diff --git itests/src/test/resources/testconfiguration.properties itests/src/test/resources/testconfiguration.properties index de14c81c10..4b1691bfa8 100644 --- itests/src/test/resources/testconfiguration.properties +++ itests/src/test/resources/testconfiguration.properties @@ -2509,7 +2509,244 @@ minillaplocal.query.files=\ merge_dynamic_partition5.q,\ merge_empty.q,\ merge_join_1.q,\ - mergejoins.q + mergejoins.q,\ + mergejoins_mixed.q,\ + metadataOnlyOptimizer.q,\ + mm_buckets.q,\ + multi_insert_distinct.q,\ + multi_insert_gby.q,\ + multi_insert_gby2.q,\ + multi_insert_gby3.q,\ + multi_insert_gby4.q,\ + multi_insert_mixed.q,\ + multi_insert_move_tasks_share_dependencies.q,\ + multi_insert_union_src.q,\ + multi_insert_with_join2.q,\ + multi_join_union.q,\ + multigroupby_singlemr.q,\ + named_column_join.q,\ + nested_column_pruning.q,\ + no_hooks.q,\ + noalias_subq1.q,\ + nonblock_op_deduplicate.q,\ + notable_alias1.q,\ + notable_alias2.q,\ + null_cast.q,\ + nullability_transitive_inference.q,\ + nullgroup.q,\ + nullgroup2.q,\ + nullgroup3.q,\ + nullgroup4.q,\ + nullgroup4_multi_distinct.q,\ + nullgroup5.q,\ + num_op_type_conv.q,\ + offset_limit_global_optimizer.q,\ + optimize_filter_literal.q,\ + optional_outer.q,\ + orc_avro_partition_uniontype.q,\ + orc_int_type_promotion.q,\ + orc_nested_column_pruning.q,\ + orc_ppd_str_conversion.q,\ + orc_schema_evolution_float.q,\ + order.q,\ + order3.q,\ + order_by_expr_1.q,\ + order_by_expr_2.q,\ + order_by_pos.q,\ + outer_join_ppr.q,\ + outer_reference_windowed.q,\ + parallel_join0.q,\ + parallel_join1.q,\ + parallel_orderby.q,\ + parquet_create.q,\ + parquet_int64_timestamp_int96_compatibility.q,\ + parquet_join.q,\ + parquet_mixed_partition_formats2.q,\ + parquet_no_row_serde.q,\ + parquet_ppd_boolean.q,\ + parquet_ppd_char.q,\ + parquet_ppd_date.q,\ + parquet_ppd_decimal.q,\ + parquet_ppd_timestamp.q,\ + parquet_ppd_varchar.q,\ + parquet_schema_evolution.q,\ + parquet_thrift_array_of_primitives.q,\ + parquet_types_non_dictionary_encoding_vectorization.q,\ + parquet_vectorization_0.q,\ + parquet_vectorization_1.q,\ + parquet_vectorization_10.q,\ + parquet_vectorization_11.q,\ + parquet_vectorization_12.q,\ + parquet_vectorization_13.q,\ + parquet_vectorization_14.q,\ + parquet_vectorization_15.q,\ + parquet_vectorization_16.q,\ + parquet_vectorization_17.q,\ + parquet_vectorization_2.q,\ + parquet_vectorization_3.q,\ + parquet_vectorization_4.q,\ + parquet_vectorization_5.q,\ + parquet_vectorization_6.q,\ + parquet_vectorization_7.q,\ + parquet_vectorization_8.q,\ + parquet_vectorization_9.q,\ + parquet_vectorization_decimal_date.q,\ + parquet_vectorization_div0.q,\ + parquet_vectorization_limit.q,\ + parquet_vectorization_offset_limit.q,\ + parquet_vectorization_part_project.q,\ + parquet_vectorization_pushdown.q,\ + partial_column_stats.q,\ + partition_boolexpr.q,\ + partition_condition_remover.q,\ + partition_timestamp2.q,\ + partition_wise_fileformat2.q,\ + pcr.q,\ + pcs.q,\ + pointlookup.q,\ + pointlookup2.q,\ + pointlookup3.q,\ + pointlookup4.q,\ + pointlookup5.q,\ + position_alias_test_1.q,\ + ppd1.q,\ + ppd2.q,\ + ppd_clusterby.q,\ + ppd_constant_expr.q,\ + ppd_deterministic_expr.q,\ + ppd_gby.q,\ + ppd_gby2.q,\ + ppd_gby_join.q,\ + ppd_join.q,\ + ppd_join2.q,\ + ppd_join3.q,\ + ppd_join4.q,\ + ppd_join5.q,\ + ppd_join_filter.q,\ + ppd_multi_insert.q,\ + ppd_outer_join1.q,\ + ppd_outer_join2.q,\ + ppd_outer_join3.q,\ + ppd_outer_join4.q,\ + ppd_outer_join5.q,\ + ppd_random.q,\ + ppd_repeated_alias.q,\ + ppd_udf_case.q,\ + ppd_udf_col.q,\ + ppd_udtf.q,\ + ppd_union.q,\ + ppd_vc.q,\ + ppd_windowing1.q,\ + ppd_windowing2.q,\ + ppr_allchildsarenull.q,\ + ppr_pushdown3.q,\ + print_header.q,\ + ptfgroupbyjoin.q,\ + push_or.q,\ + query_result_fileformat.q,\ + quote1.q,\ + quote2.q,\ + quotedid_basic.q,\ + quotedid_partition.q,\ + quotedid_skew.q,\ + rand_partitionpruner1.q,\ + rand_partitionpruner2.q,\ + rand_partitionpruner3.q,\ + rcfile_null_value.q,\ + reduceSinkDeDuplication_pRS_key_empty.q,\ + reduce_deduplicate_exclude_join.q,\ + reduce_deduplicate_extended2.q,\ + regex_col.q,\ + reloadJar.q,\ + remove_exprs_stats.q,\ + router_join_ppr.q,\ + runtime_skewjoin_mapjoin_spark.q,\ + --sample2.q,\ + sample3.q,\ + --sample4.q,\ + sample5.q,\ + sample6.q,\ + sample7.q,\ + sample8.q,\ + sample9.q,\ + select_as_omitted.q,\ + select_column_pruning.q,\ + select_same_col.q,\ + select_unquote_and.q,\ + select_unquote_not.q,\ + select_unquote_or.q,\ + semijoin2.q,\ + semijoin3.q,\ + semijoin4.q,\ + semijoin5.q,\ + serde_multi_delimit.q,\ + set_processor_namespaces.q,\ + set_variable_sub.q,\ + setop_no_distinct.q,\ + setop_subq.q,\ + show_create_table_db_table.q,\ + show_create_table_delimited.q,\ + show_create_table_temp_table.q,\ + skewjoin_mapjoin1.q,\ + skewjoin_mapjoin10.q,\ + skewjoin_mapjoin11.q,\ + skewjoin_mapjoin2.q,\ + skewjoin_mapjoin3.q,\ + skewjoin_mapjoin4.q,\ + skewjoin_mapjoin5.q,\ + skewjoin_mapjoin6.q,\ + skewjoin_mapjoin7.q,\ + skewjoin_mapjoin8.q,\ + skewjoin_mapjoin9.q,\ + skewjoin_noskew.q,\ + skewjoin_onesideskew.q,\ + skewjoin_union_remove_1.q,\ + skewjoin_union_remove_2.q,\ + sort.q,\ + source.q,\ + special_character_in_tabnames_2.q,\ + stat_estimate_drill.q,\ + stat_estimate_related_col.q,\ + stats0.q,\ + stats1.q,\ + stats10.q,\ + stats12.q,\ + stats13.q,\ + stats2.q,\ + stats4.q,\ + stats5.q,\ + stats7.q,\ + stats8.q,\ + stats9.q,\ + stats_empty_dyn_part.q,\ + stats_empty_partition.q,\ + stats_empty_partition2.q,\ + stats_nonpart.q,\ + stats_part.q,\ + stats_part2.q,\ + stats_partial_size.q,\ + stats_ppr_all.q,\ + stats_sizebug.q,\ + structin.q,\ + subq.q,\ + subq2.q,\ + subq_where_serialization.q,\ + subquery_alias.q,\ + subquery_exists_having.q,\ + subquery_multiinsert.q,\ + subquery_notexists.q,\ + subquery_notexists_having.q,\ + subquery_notin_having.q,\ + subquery_unqual_corr_expr.q,\ + subquery_unqualcolumnrefs.q,\ + tablevalues.q,\ + temp_table_add_part_multiple.q,\ + temp_table_alter_partition_coltype.q,\ + temp_table_display_colstats_tbllvl.q,\ + temp_table_insert1_overwrite_partitions.q,\ + temp_table_insert2_overwrite_partitions.q,\ + temp_table_join1.q,\ + temp_table_load_dyn_part1.q encrypted.query.files=encryption_join_unencrypted_tbl.q,\ encryption_insert_partition_static.q,\ diff --git ql/src/test/queries/clientpositive/metadataOnlyOptimizer.q ql/src/test/queries/clientpositive/metadataOnlyOptimizer.q index bafdd58022..f7694f8bb5 100644 --- ql/src/test/queries/clientpositive/metadataOnlyOptimizer.q +++ ql/src/test/queries/clientpositive/metadataOnlyOptimizer.q @@ -1,47 +1,67 @@ --! qt:dataset:srcpart --! qt:dataset:src +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; -select key from( -select '1' as key from srcpart where ds="2008-04-09" -UNION all -SELECT key from srcpart where ds="2008-04-09" and hr="11" -) tab group by key; - -select key from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -) tab group by key; - -select max(key) from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -) tab group by key; - -select key from( -SELECT '1' as key from src -UNION all -SELECT '2' as key from src -) tab group by key; - - -select key from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -UNION all -SELECT '2' as key from src -UNION all -SELECT key as key from src -) tab group by key; - -select k from (select * from (SELECT '1' as k from src limit 0)a union all select key as k from src limit 1)tab; - -select k from (select * from (SELECT '1' as k from src limit 1)a union all select key as k from src limit 0)tab; - -select max(ds) from srcpart; - -select count(ds) from srcpart; + + SELECT key + FROM (SELECT '1' AS key FROM srcpart WHERE ds="2008-04-09" + UNION ALL + SELECT key FROM srcpart WHERE ds="2008-04-09" AND hr="11") tab +GROUP BY key; + + SELECT key + FROM (SELECT '1' AS key fROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key; + + SELECT max(key) + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key; + + SELECT key + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT '2' AS key FROM src) tab +GROUP BY key; + + + SELECT key + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT key AS key FROM src + UNION ALL + SELECT '2' AS key FROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key; + +SELECT k + FROM (SELECT * + FROM (SELECT '1' AS k + FROM src + LIMIT 0) a + UNION ALL + SELECT key AS k + FROM src + ORDER BY k + LIMIT 1) tab; + +SELECT k + FROM (SELECT * + FROM (SELECT '1' AS k + FROM src + LIMIT 1) a + UNION ALL + SELECT key AS k + FROM src + LIMIT 0) tab; + +SELECT max(ds) FROM srcpart; + +SELECT count(ds) FROM srcpart; diff --git ql/src/test/queries/clientpositive/mm_buckets.q ql/src/test/queries/clientpositive/mm_buckets.q index 02ca423493..5686c8e11e 100644 --- ql/src/test/queries/clientpositive/mm_buckets.q +++ ql/src/test/queries/clientpositive/mm_buckets.q @@ -1,4 +1,6 @@ --! qt:dataset:src +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; set hive.explain.user=false; set hive.fetch.task.conversion=none; @@ -63,4 +65,4 @@ select * from bucket2_mm tablesample (bucket 1 out of 10) s order by key, id; select * from bucket2_mm tablesample (bucket 4 out of 10) s order by key, id; drop table bucket2_mm; -drop table intermediate_n2; \ No newline at end of file +drop table intermediate_n2; diff --git ql/src/test/queries/clientpositive/notable_alias1.q ql/src/test/queries/clientpositive/notable_alias1.q index 68b8982164..f2c015e50c 100644 --- ql/src/test/queries/clientpositive/notable_alias1.q +++ ql/src/test/queries/clientpositive/notable_alias1.q @@ -1,4 +1,6 @@ --! qt:dataset:src +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; CREATE TABLE dest1_n4(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE; diff --git ql/src/test/queries/clientpositive/notable_alias2.q ql/src/test/queries/clientpositive/notable_alias2.q index c1338241a7..e915ea2933 100644 --- ql/src/test/queries/clientpositive/notable_alias2.q +++ ql/src/test/queries/clientpositive/notable_alias2.q @@ -1,4 +1,6 @@ --! qt:dataset:src +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; CREATE TABLE dest1_n50(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE; diff --git ql/src/test/queries/clientpositive/orc_avro_partition_uniontype.q ql/src/test/queries/clientpositive/orc_avro_partition_uniontype.q index 1d68606e58..87e6ef0620 100644 --- ql/src/test/queries/clientpositive/orc_avro_partition_uniontype.q +++ ql/src/test/queries/clientpositive/orc_avro_partition_uniontype.q @@ -1,11 +1,12 @@ --! qt:dataset:src +-- SORT_QUERY_RESULTS set hive.vectorized.execution.enabled=false; SET hive.exec.schema.evolution = false; CREATE TABLE avro_orc_partitioned_uniontype (a uniontype) PARTITIONED BY (b int) STORED AS ORC; -INSERT INTO avro_orc_partitioned_uniontype PARTITION (b=1) SELECT create_union(1, true, value) FROM src LIMIT 5; +INSERT INTO avro_orc_partitioned_uniontype PARTITION (b=1) SELECT create_union(1, true, value) FROM src; ALTER TABLE avro_orc_partitioned_uniontype SET FILEFORMAT AVRO; diff --git ql/src/test/queries/clientpositive/orc_int_type_promotion.q ql/src/test/queries/clientpositive/orc_int_type_promotion.q index 5899dbef45..23aa862051 100644 --- ql/src/test/queries/clientpositive/orc_int_type_promotion.q +++ ql/src/test/queries/clientpositive/orc_int_type_promotion.q @@ -1,4 +1,5 @@ --! qt:dataset:srcpart +-- SORT_QUERY_RESULTS set hive.vectorized.execution.enabled=false; set hive.mapred.mode=nonstrict; @@ -70,8 +71,8 @@ SET hive.exec.schema.evolution=false; create table src_part_orc (key int, value string) partitioned by (ds string) stored as orc; insert overwrite table src_part_orc partition(ds) select key, value, ds from srcpart where ds is not null; -select * from src_part_orc limit 10; +select * from src_part_orc order by key, value limit 10; alter table src_part_orc change key key bigint; -select * from src_part_orc limit 10; +select * from src_part_orc order by key, value limit 10; reset hive.metastore.disallow.incompatible.col.type.changes; diff --git ql/src/test/queries/clientpositive/order_by_expr_2.q ql/src/test/queries/clientpositive/order_by_expr_2.q index 759186dbf9..dcc2a668af 100644 --- ql/src/test/queries/clientpositive/order_by_expr_2.q +++ ql/src/test/queries/clientpositive/order_by_expr_2.q @@ -4,8 +4,8 @@ create table t_n14(a int, b int); insert into t_n14 values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9); -select a as b, b as a from t_n14 order by a; -select a as b, b as a from t_n14 order by t_n14.a; +select a as b, b as a from t_n14 order by a, b; +select a as b, b as a from t_n14 order by t_n14.a, t_n14.b; select a as b from t_n14 order by b; select a as b from t_n14 order by 0-a; -select a,b,count(*),a+b from t_n14 group by a, b order by a+b; +select a,b,count(*),a+b from t_n14 group by a, b order by a+b, a; diff --git ql/src/test/queries/clientpositive/order_by_pos.q ql/src/test/queries/clientpositive/order_by_pos.q index ab4f226a13..738fbd5b09 100644 --- ql/src/test/queries/clientpositive/order_by_pos.q +++ ql/src/test/queries/clientpositive/order_by_pos.q @@ -4,17 +4,17 @@ create table t_n3(a int, b int); insert into t_n3 values (1,2),(1,2),(1,3),(2,4),(20,-100),(-1000,100),(4,5),(3,7),(8,9); -select * from t_n3 order by 2; +select * from t_n3 order by 2, 1; -select * from t_n3 order by 1; +select * from t_n3 order by 1, 2; select * from t_n3 union select * from t_n3 order by 1, 2; -select * from t_n3 union select * from t_n3 order by 2; +select * from t_n3 union select * from t_n3 order by 2, 1; -select * from t_n3 union select * from t_n3 order by 1; +select * from t_n3 union select * from t_n3 order by 1, 2; select * from (select a, count(a) from t_n3 group by a)subq order by 2, 1; -select * from (select a,b, count(*) from t_n3 group by a, b)subq order by 3, 2 desc; +select * from (select a,b, count(*) from t_n3 group by a, b)subq order by 3, 2 desc, 1; diff --git ql/src/test/queries/clientpositive/parquet_mixed_partition_formats2.q ql/src/test/queries/clientpositive/parquet_mixed_partition_formats2.q index 78c3b0f276..191d3d7965 100644 --- ql/src/test/queries/clientpositive/parquet_mixed_partition_formats2.q +++ ql/src/test/queries/clientpositive/parquet_mixed_partition_formats2.q @@ -17,17 +17,17 @@ OUTPUTFORMAT LOAD DATA LOCAL INPATH '../../data/files/sample2.json' INTO TABLE parquet_table_json_partition PARTITION(ts='20150101'); -SELECT * FROM parquet_table_json_partition LIMIT 100; +SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100; ALTER TABLE parquet_table_json_partition SET FILEFORMAT INPUTFORMAT 'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat' OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat' SERDE 'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'; -SELECT * FROM parquet_table_json_partition LIMIT 100; +SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100; -CREATE TABLE new_table AS SELECT * FROM parquet_table_json_partition LIMIT 100; +CREATE TABLE new_table AS SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100; -SELECT * FROM new_table; +SELECT * FROM new_table ORDER BY address, reports; diff --git ql/src/test/queries/clientpositive/parquet_ppd_boolean.q ql/src/test/queries/clientpositive/parquet_ppd_boolean.q index a4bd30ad06..499c844cda 100644 --- ql/src/test/queries/clientpositive/parquet_ppd_boolean.q +++ ql/src/test/queries/clientpositive/parquet_ppd_boolean.q @@ -1,5 +1,6 @@ --! qt:dataset:src1 --! qt:dataset:src +-- SORT_QUERY_RESULTS set hive.vectorized.execution.enabled=false; SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat; @@ -36,4 +37,4 @@ select * from newtypestbl where b=false; select * from newtypestbl where b!=false; select * from newtypestbl where bfalse; -select * from newtypestbl where b<=false; \ No newline at end of file +select * from newtypestbl where b<=false; diff --git ql/src/test/queries/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q ql/src/test/queries/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q index 0fded10ef3..b72fec5f1f 100644 --- ql/src/test/queries/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q +++ ql/src/test/queries/clientpositive/parquet_types_non_dictionary_encoding_vectorization.q @@ -92,5 +92,5 @@ SELECT cvarchar, count(*) FROM parquet_types_n1 GROUP BY cvarchar ORDER BY cvarc EXPLAIN SELECT cstring1, count(*) FROM parquet_types_n1 GROUP BY cstring1 ORDER BY cstring1; SELECT cstring1, count(*) FROM parquet_types_n1 GROUP BY cstring1 ORDER BY cstring1; -EXPLAIN SELECT hex(cbinary), count(*) FROM parquet_types_n1 GROUP BY cbinary; -SELECT hex(cbinary), count(*) FROM parquet_types_n1 GROUP BY cbinary; \ No newline at end of file +EXPLAIN SELECT hex(cbinary), count(*) FROM parquet_types_n1 GROUP BY cbinary ORDER BY cbinary; +SELECT hex(cbinary), count(*) FROM parquet_types_n1 GROUP BY cbinary ORDER BY cbinary; diff --git ql/src/test/queries/clientpositive/parquet_vectorization_limit.q ql/src/test/queries/clientpositive/parquet_vectorization_limit.q index 6dac0d6460..bc70945caf 100644 --- ql/src/test/queries/clientpositive/parquet_vectorization_limit.q +++ ql/src/test/queries/clientpositive/parquet_vectorization_limit.q @@ -6,8 +6,8 @@ set hive.fetch.task.conversion=none; -- SORT_QUERY_RESULTS -explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7; -SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7; +explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble AND cint > 0 ORDER BY cbigint, cdouble LIMIT 7; +SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble AND cint > 0 ORDER BY cbigint, cdouble LIMIT 7; set hive.optimize.reducededuplication.min.reducer=1; set hive.limit.pushdown.memory.usage=0.3f; @@ -15,8 +15,8 @@ set hive.limit.pushdown.memory.usage=0.3f; -- HIVE-3562 Some limit can be pushed down to map stage - c/p parts from limit_pushdown explain VECTORIZATION EXPRESSION -select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20; -select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20; +select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble,csmallint limit 20; +select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble,csmallint limit 20; -- deduped RS explain VECTORIZATION EXPRESSION @@ -25,8 +25,8 @@ select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by -- distincts explain VECTORIZATION EXPRESSION -select distinct(ctinyint) from alltypesparquet limit 20; -select distinct(ctinyint) from alltypesparquet limit 20; +select distinct(ctinyint) from alltypesparquet order by ctinyint limit 20; +select distinct(ctinyint) from alltypesparquet order by ctinyint limit 20; explain VECTORIZATION EXPRESSION select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20; @@ -34,8 +34,8 @@ select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint -- limit zero explain VECTORIZATION EXPRESSION -select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0; -select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0; +select ctinyint,cdouble from alltypesparquet order by ctinyint,cdouble limit 0; +select ctinyint,cdouble from alltypesparquet order by ctinyint,cdouble limit 0; -- 2MR (applied to last RS) explain VECTORIZATION EXPRESSION diff --git ql/src/test/queries/clientpositive/ppd_windowing2.q ql/src/test/queries/clientpositive/ppd_windowing2.q index 4f045a4c37..d851384c61 100644 --- ql/src/test/queries/clientpositive/ppd_windowing2.q +++ ql/src/test/queries/clientpositive/ppd_windowing2.q @@ -1,4 +1,6 @@ --! qt:dataset:src +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; set hive.optimize.ppd=true; set hive.ppd.remove.duplicatefilters=false; diff --git ql/src/test/queries/clientpositive/print_header.q ql/src/test/queries/clientpositive/print_header.q index aa7e1e04da..7ab0e6c714 100644 --- ql/src/test/queries/clientpositive/print_header.q +++ ql/src/test/queries/clientpositive/print_header.q @@ -4,14 +4,13 @@ set hive.mapred.mode=nonstrict; set hive.cli.print.header=true; -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 - LIMIT 10; + SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 + FROM (SELECT * FROM src WHERE src.key < 10) src1 + JOIN (SELECT * FROM src WHERE src.key < 10) src2 +ORDER BY k1, v1, k2, v2 + LIMIT 10; -SELECT src.key, sum(substr(src.value,5)) FROM src GROUP BY src.key LIMIT 10; +SELECT src.key, sum(substr(src.value,5)) FROM src GROUP BY src.key ORDER BY src.key LIMIT 10; use default; diff --git ql/src/test/queries/clientpositive/ptfgroupbyjoin.q ql/src/test/queries/clientpositive/ptfgroupbyjoin.q index 62472c8077..dd827361a8 100644 --- ql/src/test/queries/clientpositive/ptfgroupbyjoin.q +++ ql/src/test/queries/clientpositive/ptfgroupbyjoin.q @@ -1,3 +1,5 @@ +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; create table tlb1 (id int, fkey int, val string); create table tlb2 (fid int, name string); diff --git ql/src/test/queries/clientpositive/select_same_col.q ql/src/test/queries/clientpositive/select_same_col.q index 1c62a7c066..6e7b9edf1a 100644 --- ql/src/test/queries/clientpositive/select_same_col.q +++ ql/src/test/queries/clientpositive/select_same_col.q @@ -2,7 +2,7 @@ set hive.mapred.mode=nonstrict; set hive.cbo.enable=true; --- SORT_BEFORE_DIFF +-- SORT_QUERY_RESULTS drop table srclimit; create table srclimit as select * from src limit 10; @@ -13,7 +13,7 @@ select cast(value as binary), value from srclimit order by value; select cast(value as binary), value from srclimit order by value limit 5; -select cast(value as binary), value, key from srclimit order by value limit 5; +select cast(value as binary), value, key from srclimit order by value, key limit 5; select *, key, value from srclimit; diff --git ql/src/test/queries/clientpositive/setop_no_distinct.q ql/src/test/queries/clientpositive/setop_no_distinct.q index 798f9c76c8..3917d34e11 100644 --- ql/src/test/queries/clientpositive/setop_no_distinct.q +++ ql/src/test/queries/clientpositive/setop_no_distinct.q @@ -1,3 +1,5 @@ +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; set hive.cbo.enable=true; diff --git ql/src/test/queries/clientpositive/smb_mapjoin_46.q ql/src/test/queries/clientpositive/smb_mapjoin_46.q index df52226d7e..c755d344dc 100644 --- ql/src/test/queries/clientpositive/smb_mapjoin_46.q +++ ql/src/test/queries/clientpositive/smb_mapjoin_46.q @@ -1,3 +1,5 @@ +-- SORT_QUERY_RESULTS + set hive.strict.checks.cartesian.product=false; set hive.auto.convert.join=true; set hive.auto.convert.sortmerge.join=true; diff --git ql/src/test/queries/clientpositive/subq2.q ql/src/test/queries/clientpositive/subq2.q index 12863b9269..a8634e568d 100644 --- ql/src/test/queries/clientpositive/subq2.q +++ ql/src/test/queries/clientpositive/subq2.q @@ -1,4 +1,6 @@ --! qt:dataset:src +-- SORT_QUERY_RESULTS + set hive.mapred.mode=nonstrict; EXPLAIN SELECT a.k, a.c diff --git ql/src/test/queries/clientpositive/subquery_notexists.q ql/src/test/queries/clientpositive/subquery_notexists.q index eab5d9ecd2..085ecd15f7 100644 --- ql/src/test/queries/clientpositive/subquery_notexists.q +++ ql/src/test/queries/clientpositive/subquery_notexists.q @@ -1,5 +1,6 @@ --! qt:dataset:src --! qt:dataset:part +-- SORT_QUERY_RESULTS set hive.mapred.mode=nonstrict; diff --git ql/src/test/results/clientpositive/llap/mergejoins_mixed.q.out ql/src/test/results/clientpositive/llap/mergejoins_mixed.q.out new file mode 100644 index 0000000000..3751294882 --- /dev/null +++ ql/src/test/results/clientpositive/llap/mergejoins_mixed.q.out @@ -0,0 +1,1773 @@ +PREHOOK: query: create table a_n5 (key string, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@a_n5 +POSTHOOK: query: create table a_n5 (key string, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@a_n5 +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) full outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) full outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (c.key=d.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@a_n5 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (c.key=d.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@a_n5 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a_n5 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col4 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col4 (type: string) + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col4 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/metadataOnlyOptimizer.q.out ql/src/test/results/clientpositive/llap/metadataOnlyOptimizer.q.out similarity index 72% rename from ql/src/test/results/clientpositive/metadataOnlyOptimizer.q.out rename to ql/src/test/results/clientpositive/llap/metadataOnlyOptimizer.q.out index 1671c6b8b4..f1746dee77 100644 --- ql/src/test/results/clientpositive/metadataOnlyOptimizer.q.out +++ ql/src/test/results/clientpositive/llap/metadataOnlyOptimizer.q.out @@ -1,18 +1,18 @@ -PREHOOK: query: select key from( -select '1' as key from srcpart where ds="2008-04-09" -UNION all -SELECT key from srcpart where ds="2008-04-09" and hr="11" -) tab group by key +PREHOOK: query: SELECT key + FROM (SELECT '1' AS key FROM srcpart WHERE ds="2008-04-09" + UNION ALL + SELECT key FROM srcpart WHERE ds="2008-04-09" AND hr="11") tab +GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### -POSTHOOK: query: select key from( -select '1' as key from srcpart where ds="2008-04-09" -UNION all -SELECT key from srcpart where ds="2008-04-09" and hr="11" -) tab group by key +POSTHOOK: query: SELECT key + FROM (SELECT '1' AS key FROM srcpart WHERE ds="2008-04-09" + UNION ALL + SELECT key FROM srcpart WHERE ds="2008-04-09" AND hr="11") tab +GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 @@ -328,19 +328,19 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 96 97 98 -PREHOOK: query: select key from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -) tab group by key +PREHOOK: query: SELECT key + FROM (SELECT '1' AS key fROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select key from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -) tab group by key +POSTHOOK: query: SELECT key + FROM (SELECT '1' AS key fROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### @@ -654,19 +654,19 @@ POSTHOOK: Input: default@src 96 97 98 -PREHOOK: query: select max(key) from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -) tab group by key +PREHOOK: query: SELECT max(key) + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select max(key) from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -) tab group by key +POSTHOOK: query: SELECT max(key) + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### @@ -980,45 +980,45 @@ POSTHOOK: Input: default@src 96 97 98 -PREHOOK: query: select key from( -SELECT '1' as key from src -UNION all -SELECT '2' as key from src -) tab group by key +PREHOOK: query: SELECT key + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT '2' AS key FROM src) tab +GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select key from( -SELECT '1' as key from src -UNION all -SELECT '2' as key from src -) tab group by key +POSTHOOK: query: SELECT key + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT '2' AS key FROM src) tab +GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### 1 2 -PREHOOK: query: select key from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -UNION all -SELECT '2' as key from src -UNION all -SELECT key as key from src -) tab group by key +PREHOOK: query: SELECT key + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT key AS key FROM src + UNION ALL + SELECT '2' AS key FROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select key from( -SELECT '1' as key from src -UNION all -SELECT key as key from src -UNION all -SELECT '2' as key from src -UNION all -SELECT key as key from src -) tab group by key +POSTHOOK: query: SELECT key + FROM (SELECT '1' AS key FROM src + UNION ALL + SELECT key AS key FROM src + UNION ALL + SELECT '2' AS key FROM src + UNION ALL + SELECT key AS key FROM src) tab +GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### @@ -1332,24 +1332,58 @@ POSTHOOK: Input: default@src 96 97 98 -PREHOOK: query: select k from (select * from (SELECT '1' as k from src limit 0)a union all select key as k from src limit 1)tab +PREHOOK: query: SELECT k + FROM (SELECT * + FROM (SELECT '1' AS k + FROM src + LIMIT 0) a + UNION ALL + SELECT key AS k + FROM src + ORDER BY k + LIMIT 1) tab PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select k from (select * from (SELECT '1' as k from src limit 0)a union all select key as k from src limit 1)tab +POSTHOOK: query: SELECT k + FROM (SELECT * + FROM (SELECT '1' AS k + FROM src + LIMIT 0) a + UNION ALL + SELECT key AS k + FROM src + ORDER BY k + LIMIT 1) tab POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -238 -PREHOOK: query: select k from (select * from (SELECT '1' as k from src limit 1)a union all select key as k from src limit 0)tab +0 +PREHOOK: query: SELECT k + FROM (SELECT * + FROM (SELECT '1' AS k + FROM src + LIMIT 1) a + UNION ALL + SELECT key AS k + FROM src + LIMIT 0) tab PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select k from (select * from (SELECT '1' as k from src limit 1)a union all select key as k from src limit 0)tab +POSTHOOK: query: SELECT k + FROM (SELECT * + FROM (SELECT '1' AS k + FROM src + LIMIT 1) a + UNION ALL + SELECT key AS k + FROM src + LIMIT 0) tab POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -PREHOOK: query: select max(ds) from srcpart +PREHOOK: query: SELECT max(ds) FROM srcpart PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 @@ -1357,7 +1391,7 @@ PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### -POSTHOOK: query: select max(ds) from srcpart +POSTHOOK: query: SELECT max(ds) FROM srcpart POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 @@ -1366,7 +1400,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 2008-04-09 -PREHOOK: query: select count(ds) from srcpart +PREHOOK: query: SELECT count(ds) FROM srcpart PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 @@ -1374,7 +1408,7 @@ PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### -POSTHOOK: query: select count(ds) from srcpart +POSTHOOK: query: SELECT count(ds) FROM srcpart POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 diff --git ql/src/test/results/clientpositive/mm_buckets.q.out ql/src/test/results/clientpositive/llap/mm_buckets.q.out similarity index 100% rename from ql/src/test/results/clientpositive/mm_buckets.q.out rename to ql/src/test/results/clientpositive/llap/mm_buckets.q.out index e2c31637fa..d5e33ffbc5 100644 --- ql/src/test/results/clientpositive/mm_buckets.q.out +++ ql/src/test/results/clientpositive/llap/mm_buckets.q.out @@ -79,10 +79,10 @@ POSTHOOK: Input: default@bucket0_mm #### A masked pattern was here #### 0 0 10 10 -97 97 -98 98 100 100 103 103 +97 97 +98 98 PREHOOK: query: select * from bucket0_mm tablesample (bucket 1 out of 2) s PREHOOK: type: QUERY PREHOOK: Input: default@bucket0_mm @@ -133,14 +133,14 @@ POSTHOOK: Input: default@bucket0_mm 0 0 10 10 10 10 -97 97 -97 97 -98 98 -98 98 100 100 100 100 103 103 103 103 +97 97 +97 97 +98 98 +98 98 PREHOOK: query: select * from bucket0_mm tablesample (bucket 1 out of 2) s PREHOOK: type: QUERY PREHOOK: Input: default@bucket0_mm @@ -150,10 +150,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@bucket0_mm #### A masked pattern was here #### 10 10 -97 97 -98 98 10 10 97 97 +97 97 +98 98 98 98 PREHOOK: query: select * from bucket0_mm tablesample (bucket 2 out of 2) s PREHOOK: type: QUERY @@ -164,10 +164,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@bucket0_mm #### A masked pattern was here #### 0 0 -100 100 -103 103 0 0 100 100 +100 100 +103 103 103 103 PREHOOK: query: drop table bucket0_mm PREHOOK: type: DROPTABLE @@ -277,16 +277,16 @@ POSTHOOK: Input: default@bucket1_mm@key2=99 #### A masked pattern was here #### -1 0 1 1 0 -1 -9 10 11 +101 100 99 +102 103 104 +104 103 102 11 10 9 +9 10 11 96 97 98 97 98 99 98 97 96 -99 98 97 99 100 101 -101 100 99 -102 103 104 -104 103 102 +99 98 97 PREHOOK: query: select * from bucket1_mm tablesample (bucket 1 out of 2) s order by key, id PREHOOK: type: QUERY PREHOOK: Input: default@bucket1_mm @@ -317,12 +317,12 @@ POSTHOOK: Input: default@bucket1_mm@key2=97 POSTHOOK: Input: default@bucket1_mm@key2=98 POSTHOOK: Input: default@bucket1_mm@key2=99 #### A masked pattern was here #### +101 100 99 96 97 98 97 98 99 98 97 96 -99 98 97 99 100 101 -101 100 99 +99 98 97 PREHOOK: query: select * from bucket1_mm tablesample (bucket 2 out of 2) s order by key, id PREHOOK: type: QUERY PREHOOK: Input: default@bucket1_mm @@ -355,10 +355,10 @@ POSTHOOK: Input: default@bucket1_mm@key2=99 #### A masked pattern was here #### -1 0 1 1 0 -1 -9 10 11 -11 10 9 102 103 104 104 103 102 +11 10 9 +9 10 11 PREHOOK: query: drop table bucket1_mm PREHOOK: type: DROPTABLE PREHOOK: Input: default@bucket1_mm @@ -448,9 +448,9 @@ POSTHOOK: query: select * from bucket2_mm POSTHOOK: type: QUERY POSTHOOK: Input: default@bucket2_mm #### A masked pattern was here #### -103 103 0 0 0 0 +103 103 PREHOOK: query: select * from bucket2_mm tablesample (bucket 1 out of 10) s order by key, id PREHOOK: type: QUERY PREHOOK: Input: default@bucket2_mm diff --git ql/src/test/results/clientpositive/llap/multi_insert_distinct.q.out ql/src/test/results/clientpositive/llap/multi_insert_distinct.q.out new file mode 100644 index 0000000000..4d22b33bb5 --- /dev/null +++ ql/src/test/results/clientpositive/llap/multi_insert_distinct.q.out @@ -0,0 +1,576 @@ +PREHOOK: query: CREATE TABLE tmp1 ( v1 string , v2 string , v3 string ) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY '\t' +LINES TERMINATED BY '\n' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmp1 +POSTHOOK: query: CREATE TABLE tmp1 ( v1 string , v2 string , v3 string ) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY '\t' +LINES TERMINATED BY '\n' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmp1 +PREHOOK: query: INSERT INTO tmp1 VALUES ('v1', 'v2', 'v3'), ('v1', 'v2', 'v3a') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@tmp1 +POSTHOOK: query: INSERT INTO tmp1 VALUES ('v1', 'v2', 'v3'), ('v1', 'v2', 'v3a') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@tmp1 +POSTHOOK: Lineage: tmp1.v1 SCRIPT [] +POSTHOOK: Lineage: tmp1.v2 SCRIPT [] +POSTHOOK: Lineage: tmp1.v3 SCRIPT [] +PREHOOK: query: CREATE TABLE tmp_grouped_by_all_col ( v1 string , v2 string , v3 string ) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmp_grouped_by_all_col +POSTHOOK: query: CREATE TABLE tmp_grouped_by_all_col ( v1 string , v2 string , v3 string ) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmp_grouped_by_all_col +PREHOOK: query: CREATE TABLE tmp_grouped_by_one_col ( v1 string , cnt__v2 int , cnt__v3 int ) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: query: CREATE TABLE tmp_grouped_by_one_col ( v1 string , cnt__v2 int , cnt__v3 int ) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmp_grouped_by_one_col +PREHOOK: query: CREATE TABLE tmp_grouped_by_two_col ( v1 string , v2 string , cnt__v3 int ) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: query: CREATE TABLE tmp_grouped_by_two_col ( v1 string , v2 string , cnt__v3 int ) +ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmp_grouped_by_two_col +PREHOOK: query: explain FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp1 +PREHOOK: Output: default@tmp_grouped_by_one_col +PREHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: query: explain FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp1 +POSTHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: Output: default@tmp_grouped_by_two_col +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tmp1 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: v1 (type: string), v2 (type: string), v3 (type: string) + outputColumnNames: v1, v2, v3 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT v2), count(DISTINCT v3) + keys: v1 (type: string), v2 (type: string), v3 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: v1 (type: string), v2 (type: string), v3 (type: string) + outputColumnNames: v1, v2, v3 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT v3) + keys: v1 (type: string), v2 (type: string), v3 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_one_col + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col2:0._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_two_col + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_one_col + + Stage: Stage-1 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_two_col + +PREHOOK: query: FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp1 +PREHOOK: Output: default@tmp_grouped_by_one_col +PREHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: query: FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp1 +POSTHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v2 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_one_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_two_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_two_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_two_col.v2 SIMPLE [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] +PREHOOK: query: select * from tmp_grouped_by_two_col +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp_grouped_by_two_col +#### A masked pattern was here #### +POSTHOOK: query: select * from tmp_grouped_by_two_col +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp_grouped_by_two_col +#### A masked pattern was here #### +v1 v2 2 +PREHOOK: query: truncate table tmp_grouped_by_two_col +PREHOOK: type: TRUNCATETABLE +PREHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: query: truncate table tmp_grouped_by_two_col +POSTHOOK: type: TRUNCATETABLE +POSTHOOK: Output: default@tmp_grouped_by_two_col +PREHOOK: query: explain FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(v3) GROUP BY v1, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp1 +PREHOOK: Output: default@tmp_grouped_by_one_col +PREHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: query: explain FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(v3) GROUP BY v1, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp1 +POSTHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: Output: default@tmp_grouped_by_two_col +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tmp1 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: v1 (type: string), v2 (type: string), v3 (type: string) + outputColumnNames: v1, v2, v3 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT v2), count(DISTINCT v3) + keys: v1 (type: string), v2 (type: string), v3 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: v1 (type: string), v2 (type: string), v3 (type: string) + outputColumnNames: v1, v2, v3 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(v3) + keys: v1 (type: string), v2 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_one_col + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_two_col + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_one_col + + Stage: Stage-1 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_two_col + +PREHOOK: query: FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(v3) GROUP BY v1, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp1 +PREHOOK: Output: default@tmp_grouped_by_one_col +PREHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: query: FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_two_col +SELECT v1, v2, count(v3) GROUP BY v1, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp1 +POSTHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: Output: default@tmp_grouped_by_two_col +POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v2 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_one_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_two_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_two_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_two_col.v2 SIMPLE [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] +PREHOOK: query: select * from tmp_grouped_by_two_col +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp_grouped_by_two_col +#### A masked pattern was here #### +POSTHOOK: query: select * from tmp_grouped_by_two_col +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp_grouped_by_two_col +#### A masked pattern was here #### +v1 v2 2 +PREHOOK: query: explain FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_all_col +SELECT v1, v2, v3 GROUP BY v1, v2, v3 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp1 +PREHOOK: Output: default@tmp_grouped_by_all_col +PREHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: query: explain FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_all_col +SELECT v1, v2, v3 GROUP BY v1, v2, v3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp1 +POSTHOOK: Output: default@tmp_grouped_by_all_col +POSTHOOK: Output: default@tmp_grouped_by_one_col +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tmp1 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: v1 (type: string), v2 (type: string), v3 (type: string) + outputColumnNames: v1, v2, v3 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT v2), count(DISTINCT v3) + keys: v1 (type: string), v2 (type: string), v3 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: v1 (type: string), v2 (type: string), v3 (type: string) + outputColumnNames: v1, v2, v3 + Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: v1 (type: string), v2 (type: string), v3 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_one_col + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_all_col + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_one_col + + Stage: Stage-1 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmp_grouped_by_all_col + +PREHOOK: query: FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_all_col +SELECT v1, v2, v3 GROUP BY v1, v2, v3 +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp1 +PREHOOK: Output: default@tmp_grouped_by_all_col +PREHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: query: FROM tmp1 +INSERT INTO tmp_grouped_by_one_col +SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 +INSERT INTO tmp_grouped_by_all_col +SELECT v1, v2, v3 GROUP BY v1, v2, v3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp1 +POSTHOOK: Output: default@tmp_grouped_by_all_col +POSTHOOK: Output: default@tmp_grouped_by_one_col +POSTHOOK: Lineage: tmp_grouped_by_all_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_all_col.v2 SIMPLE [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_all_col.v3 SIMPLE [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v2 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] +POSTHOOK: Lineage: tmp_grouped_by_one_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] +PREHOOK: query: select * from tmp_grouped_by_all_col +PREHOOK: type: QUERY +PREHOOK: Input: default@tmp_grouped_by_all_col +#### A masked pattern was here #### +POSTHOOK: query: select * from tmp_grouped_by_all_col +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmp_grouped_by_all_col +#### A masked pattern was here #### +v1 v2 v3 +v1 v2 v3a diff --git ql/src/test/results/clientpositive/llap/multi_insert_gby.q.out ql/src/test/results/clientpositive/llap/multi_insert_gby.q.out new file mode 100644 index 0000000000..57a94217b8 --- /dev/null +++ ql/src/test/results/clientpositive/llap/multi_insert_gby.q.out @@ -0,0 +1,872 @@ +PREHOOK: query: create table e1_n0 (key string, count int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e1_n0 +POSTHOOK: query: create table e1_n0 (key string, count int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e1_n0 +PREHOOK: query: create table e2_n1 (key string, count int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e2_n1 +POSTHOOK: query: create table e2_n1 (key string, count int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e2_n1 +PREHOOK: query: explain FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n0 +PREHOOK: Output: default@e2_n1 +POSTHOOK: query: explain FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n0 +POSTHOOK: Output: default@e2_n1 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > 500) or (key > 450)) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > 500) or (key > 450)) (type: boolean) + Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 > 450) (type: boolean) + Statistics: Num rows: 110 Data size: 9570 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n0 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, count + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (KEY._col0 > 500) (type: boolean) + Statistics: Num rows: 110 Data size: 9570 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n1 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, count + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n0 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, count + Column Types: string, int + Table: default.e1_n0 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n1 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, count + Column Types: string, int + Table: default.e2_n1 + +PREHOOK: query: FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n0 +PREHOOK: Output: default@e2_n1 +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n0 +POSTHOOK: Output: default@e2_n1 +POSTHOOK: Lineage: e1_n0.count EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: e1_n0.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n1.count EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: e2_n1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +PREHOOK: query: select * from e1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@e1_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * from e1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e1_n0 +#### A masked pattern was here #### +452 1 +453 1 +454 3 +455 1 +457 1 +458 2 +459 2 +460 1 +462 2 +463 2 +466 3 +467 1 +468 4 +469 5 +470 1 +472 1 +475 1 +477 1 +478 2 +479 1 +480 3 +481 1 +482 1 +483 1 +484 1 +485 1 +487 1 +489 4 +490 1 +491 1 +492 2 +493 1 +494 1 +495 1 +496 1 +497 1 +498 3 +PREHOOK: query: select * from e2_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@e2_n1 +#### A masked pattern was here #### +POSTHOOK: query: select * from e2_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e2_n1 +#### A masked pattern was here #### +PREHOOK: query: explain FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) GROUP BY key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n0 +PREHOOK: Output: default@e2_n1 +POSTHOOK: query: explain FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) GROUP BY key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n0 +POSTHOOK: Output: default@e2_n1 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n1 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, count + Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (KEY._col0 > 450) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n0 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, count + Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n1 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, count + Column Types: string, int + Table: default.e2_n1 + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n0 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, count + Column Types: string, int + Table: default.e1_n0 + +PREHOOK: query: FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) GROUP BY key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n0 +PREHOOK: Output: default@e2_n1 +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE e1_n0 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n1 + SELECT key, COUNT(*) GROUP BY key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n0 +POSTHOOK: Output: default@e2_n1 +POSTHOOK: Lineage: e1_n0.count EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: e1_n0.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n1.count EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: e2_n1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +PREHOOK: query: select * from e1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@e1_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * from e1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e1_n0 +#### A masked pattern was here #### +452 1 +453 1 +454 3 +455 1 +457 1 +458 2 +459 2 +460 1 +462 2 +463 2 +466 3 +467 1 +468 4 +469 5 +470 1 +472 1 +475 1 +477 1 +478 2 +479 1 +480 3 +481 1 +482 1 +483 1 +484 1 +485 1 +487 1 +489 4 +490 1 +491 1 +492 2 +493 1 +494 1 +495 1 +496 1 +497 1 +498 3 +PREHOOK: query: select * from e2_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@e2_n1 +#### A masked pattern was here #### +POSTHOOK: query: select * from e2_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e2_n1 +#### A masked pattern was here #### +0 3 +10 1 +100 2 +103 2 +104 2 +105 1 +11 1 +111 1 +113 2 +114 1 +116 1 +118 2 +119 3 +12 2 +120 2 +125 2 +126 1 +128 3 +129 2 +131 1 +133 1 +134 2 +136 1 +137 2 +138 4 +143 1 +145 1 +146 2 +149 2 +15 2 +150 1 +152 2 +153 1 +155 1 +156 1 +157 1 +158 1 +160 1 +162 1 +163 1 +164 2 +165 2 +166 1 +167 3 +168 1 +169 4 +17 1 +170 1 +172 2 +174 2 +175 2 +176 2 +177 1 +178 1 +179 2 +18 2 +180 1 +181 1 +183 1 +186 1 +187 3 +189 1 +19 1 +190 1 +191 2 +192 1 +193 3 +194 1 +195 2 +196 1 +197 2 +199 3 +2 1 +20 1 +200 2 +201 1 +202 1 +203 2 +205 2 +207 2 +208 3 +209 2 +213 2 +214 1 +216 2 +217 2 +218 1 +219 2 +221 2 +222 1 +223 2 +224 2 +226 1 +228 1 +229 2 +230 5 +233 2 +235 1 +237 2 +238 2 +239 2 +24 2 +241 1 +242 2 +244 1 +247 1 +248 1 +249 1 +252 1 +255 2 +256 2 +257 1 +258 1 +26 2 +260 1 +262 1 +263 1 +265 2 +266 1 +27 1 +272 2 +273 3 +274 1 +275 1 +277 4 +278 2 +28 1 +280 2 +281 2 +282 2 +283 1 +284 1 +285 1 +286 1 +287 1 +288 2 +289 1 +291 1 +292 1 +296 1 +298 3 +30 1 +302 1 +305 1 +306 1 +307 2 +308 1 +309 2 +310 1 +311 3 +315 1 +316 3 +317 2 +318 3 +321 2 +322 2 +323 1 +325 2 +327 3 +33 1 +331 2 +332 1 +333 2 +335 1 +336 1 +338 1 +339 1 +34 1 +341 1 +342 2 +344 2 +345 1 +348 5 +35 3 +351 1 +353 2 +356 1 +360 1 +362 1 +364 1 +365 1 +366 1 +367 2 +368 1 +369 3 +37 2 +373 1 +374 1 +375 1 +377 1 +378 1 +379 1 +382 2 +384 3 +386 1 +389 1 +392 1 +393 1 +394 1 +395 2 +396 3 +397 2 +399 2 +4 1 +400 1 +401 5 +402 1 +403 3 +404 2 +406 4 +407 1 +409 3 +41 1 +411 1 +413 2 +414 2 +417 3 +418 1 +419 1 +42 2 +421 1 +424 2 +427 1 +429 2 +43 1 +430 3 +431 3 +432 1 +435 1 +436 1 +437 1 +438 3 +439 2 +44 1 +443 1 +444 1 +446 1 +448 1 +449 1 +452 1 +453 1 +454 3 +455 1 +457 1 +458 2 +459 2 +460 1 +462 2 +463 2 +466 3 +467 1 +468 4 +469 5 +47 1 +470 1 +472 1 +475 1 +477 1 +478 2 +479 1 +480 3 +481 1 +482 1 +483 1 +484 1 +485 1 +487 1 +489 4 +490 1 +491 1 +492 2 +493 1 +494 1 +495 1 +496 1 +497 1 +498 3 +5 3 +51 2 +53 1 +54 1 +57 1 +58 2 +64 1 +65 1 +66 1 +67 2 +69 1 +70 3 +72 2 +74 1 +76 2 +77 1 +78 1 +8 1 +80 1 +82 1 +83 2 +84 2 +85 1 +86 1 +87 1 +9 1 +90 3 +92 1 +95 2 +96 1 +97 2 +98 2 diff --git ql/src/test/results/clientpositive/multi_insert_gby2.q.out ql/src/test/results/clientpositive/llap/multi_insert_gby2.q.out similarity index 54% rename from ql/src/test/results/clientpositive/multi_insert_gby2.q.out rename to ql/src/test/results/clientpositive/llap/multi_insert_gby2.q.out index c3db38642b..42d167ec20 100644 --- ql/src/test/results/clientpositive/multi_insert_gby2.q.out +++ ql/src/test/results/clientpositive/llap/multi_insert_gby2.q.out @@ -36,101 +36,106 @@ POSTHOOK: Output: default@e1 POSTHOOK: Output: default@e2_n0 STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - Stage-1 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToDouble(key) (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToDouble(key) (type: double) + outputColumnNames: _col1 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: double) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1 - Select Operator - expressions: _col0 (type: int) - outputColumnNames: count - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: compute_stats(count, 'hll') + aggregations: count() mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: struct) + expressions: UDFToInteger(_col0) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Group By Operator - aggregations: percentile_approx(VALUE._col0, 0.5) - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n0 - Select Operator - expressions: _col0 (type: double) - outputColumnNames: percentile - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(percentile, 'hll') - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: struct) + name: default.e1 + Select Operator + expressions: _col0 (type: int) + outputColumnNames: count + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(count, 'hll') + mode: complete + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Group By Operator + aggregations: percentile_approx(VALUE._col0, 0.5) + mode: complete outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n0 + Select Operator + expressions: _col0 (type: double) + outputColumnNames: percentile + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(percentile, 'hll') + mode: complete + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection Stage: Stage-0 Move Operator @@ -142,7 +147,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.e1 - Stage: Stage-3 + Stage: Stage-4 Stats Work Basic Stats Work: Column Stats Desc: @@ -160,7 +165,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.e2_n0 - Stage: Stage-4 + Stage: Stage-5 Stats Work Basic Stats Work: Column Stats Desc: diff --git ql/src/test/results/clientpositive/llap/multi_insert_gby3.q.out ql/src/test/results/clientpositive/llap/multi_insert_gby3.q.out new file mode 100644 index 0000000000..0777184745 --- /dev/null +++ ql/src/test/results/clientpositive/llap/multi_insert_gby3.q.out @@ -0,0 +1,2321 @@ +PREHOOK: query: create table e1_n2 (key string, keyD double) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e1_n2 +POSTHOOK: query: create table e1_n2 (key string, keyD double) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e1_n2 +PREHOOK: query: create table e2_n3 (key string, keyD double, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e2_n3 +POSTHOOK: query: create table e2_n3 (key string, keyD double, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e2_n3 +PREHOOK: query: create table e3 (key string, keyD double) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e3 +POSTHOOK: query: create table e3 (key string, keyD double) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e3 +PREHOOK: query: explain +FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n2 +PREHOOK: Output: default@e2_n3 +POSTHOOK: query: explain +FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n2 +POSTHOOK: Output: default@e2_n3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT _col2) + keys: _col0 (type: string), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: double) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: key, keyd + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n3 + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) + outputColumnNames: key, keyd, value + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd + Column Types: string, double + Table: default.e1_n2 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd, value + Column Types: string, double, string + Table: default.e2_n3 + +PREHOOK: query: explain +FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n2 +PREHOOK: Output: default@e2_n3 +POSTHOOK: query: explain +FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n2 +POSTHOOK: Output: default@e2_n3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: double) + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT _col2) + keys: _col0 (type: string), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n3 + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) + outputColumnNames: key, keyd, value + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: key, keyd + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n3 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd, value + Column Types: string, double, string + Table: default.e2_n3 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd + Column Types: string, double + Table: default.e1_n2 + +PREHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n2 +PREHOOK: Output: default@e2_n3 +POSTHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n2 +POSTHOOK: Output: default@e2_n3 +POSTHOOK: Lineage: e1_n2.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e1_n2.keyd EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n3.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n3.keyd EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from e1_n2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e1_n2 +#### A masked pattern was here #### +POSTHOOK: query: select * from e1_n2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e1_n2 +#### A masked pattern was here #### +0 1.0 +10 1.0 +100 1.0 +103 1.0 +104 1.0 +105 1.0 +11 1.0 +111 1.0 +113 1.0 +114 1.0 +116 1.0 +118 1.0 +119 1.0 +12 1.0 +120 1.0 +125 1.0 +126 1.0 +128 1.0 +129 1.0 +131 1.0 +133 1.0 +134 1.0 +136 1.0 +137 1.0 +138 1.0 +143 1.0 +145 1.0 +146 1.0 +149 1.0 +15 1.0 +150 1.0 +152 1.0 +153 1.0 +155 1.0 +156 1.0 +157 1.0 +158 1.0 +160 1.0 +162 1.0 +163 1.0 +164 1.0 +165 1.0 +166 1.0 +167 1.0 +168 1.0 +169 1.0 +17 1.0 +170 1.0 +172 1.0 +174 1.0 +175 1.0 +176 1.0 +177 1.0 +178 1.0 +179 1.0 +18 1.0 +180 1.0 +181 1.0 +183 1.0 +186 1.0 +187 1.0 +189 1.0 +19 1.0 +190 1.0 +191 1.0 +192 1.0 +193 1.0 +194 1.0 +195 1.0 +196 1.0 +197 1.0 +199 1.0 +2 1.0 +20 1.0 +200 1.0 +201 1.0 +202 1.0 +203 1.0 +205 1.0 +207 1.0 +208 1.0 +209 1.0 +213 1.0 +214 1.0 +216 1.0 +217 1.0 +218 1.0 +219 1.0 +221 1.0 +222 1.0 +223 1.0 +224 1.0 +226 1.0 +228 1.0 +229 1.0 +230 1.0 +233 1.0 +235 1.0 +237 1.0 +238 1.0 +239 1.0 +24 1.0 +241 1.0 +242 1.0 +244 1.0 +247 1.0 +248 1.0 +249 1.0 +252 1.0 +255 1.0 +256 1.0 +257 1.0 +258 1.0 +26 1.0 +260 1.0 +262 1.0 +263 1.0 +265 1.0 +266 1.0 +27 1.0 +272 1.0 +273 1.0 +274 1.0 +275 1.0 +277 1.0 +278 1.0 +28 1.0 +280 1.0 +281 1.0 +282 1.0 +283 1.0 +284 1.0 +285 1.0 +286 1.0 +287 1.0 +288 1.0 +289 1.0 +291 1.0 +292 1.0 +296 1.0 +298 1.0 +30 1.0 +302 1.0 +305 1.0 +306 1.0 +307 1.0 +308 1.0 +309 1.0 +310 1.0 +311 1.0 +315 1.0 +316 1.0 +317 1.0 +318 1.0 +321 1.0 +322 1.0 +323 1.0 +325 1.0 +327 1.0 +33 1.0 +331 1.0 +332 1.0 +333 1.0 +335 1.0 +336 1.0 +338 1.0 +339 1.0 +34 1.0 +341 1.0 +342 1.0 +344 1.0 +345 1.0 +348 1.0 +35 1.0 +351 1.0 +353 1.0 +356 1.0 +360 1.0 +362 1.0 +364 1.0 +365 1.0 +366 1.0 +367 1.0 +368 1.0 +369 1.0 +37 1.0 +373 1.0 +374 1.0 +375 1.0 +377 1.0 +378 1.0 +379 1.0 +382 1.0 +384 1.0 +386 1.0 +389 1.0 +392 1.0 +393 1.0 +394 1.0 +395 1.0 +396 1.0 +397 1.0 +399 1.0 +4 1.0 +400 1.0 +401 1.0 +402 1.0 +403 1.0 +404 1.0 +406 1.0 +407 1.0 +409 1.0 +41 1.0 +411 1.0 +413 1.0 +414 1.0 +417 1.0 +418 1.0 +419 1.0 +42 1.0 +421 1.0 +424 1.0 +427 1.0 +429 1.0 +43 1.0 +430 1.0 +431 1.0 +432 1.0 +435 1.0 +436 1.0 +437 1.0 +438 1.0 +439 1.0 +44 1.0 +443 1.0 +444 1.0 +446 1.0 +448 1.0 +449 1.0 +452 1.0 +453 1.0 +454 1.0 +455 1.0 +457 1.0 +458 1.0 +459 1.0 +460 1.0 +462 1.0 +463 1.0 +466 1.0 +467 1.0 +468 1.0 +469 1.0 +47 1.0 +470 1.0 +472 1.0 +475 1.0 +477 1.0 +478 1.0 +479 1.0 +480 1.0 +481 1.0 +482 1.0 +483 1.0 +484 1.0 +485 1.0 +487 1.0 +489 1.0 +490 1.0 +491 1.0 +492 1.0 +493 1.0 +494 1.0 +495 1.0 +496 1.0 +497 1.0 +498 1.0 +5 1.0 +51 1.0 +53 1.0 +54 1.0 +57 1.0 +58 1.0 +64 1.0 +65 1.0 +66 1.0 +67 1.0 +69 1.0 +70 1.0 +72 1.0 +74 1.0 +76 1.0 +77 1.0 +78 1.0 +8 1.0 +80 1.0 +82 1.0 +83 1.0 +84 1.0 +85 1.0 +86 1.0 +87 1.0 +9 1.0 +90 1.0 +92 1.0 +95 1.0 +96 1.0 +97 1.0 +98 1.0 +PREHOOK: query: select * from e2_n3 +PREHOOK: type: QUERY +PREHOOK: Input: default@e2_n3 +#### A masked pattern was here #### +POSTHOOK: query: select * from e2_n3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e2_n3 +#### A masked pattern was here #### +0 0.0 val_0 +10 10.0 val_10 +100 200.0 val_100 +103 206.0 val_103 +104 208.0 val_104 +105 105.0 val_105 +11 11.0 val_11 +111 111.0 val_111 +113 226.0 val_113 +114 114.0 val_114 +116 116.0 val_116 +118 236.0 val_118 +119 357.0 val_119 +12 24.0 val_12 +120 240.0 val_120 +125 250.0 val_125 +126 126.0 val_126 +128 384.0 val_128 +129 258.0 val_129 +131 131.0 val_131 +133 133.0 val_133 +134 268.0 val_134 +136 136.0 val_136 +137 274.0 val_137 +138 552.0 val_138 +143 143.0 val_143 +145 145.0 val_145 +146 292.0 val_146 +149 298.0 val_149 +15 30.0 val_15 +150 150.0 val_150 +152 304.0 val_152 +153 153.0 val_153 +155 155.0 val_155 +156 156.0 val_156 +157 157.0 val_157 +158 158.0 val_158 +160 160.0 val_160 +162 162.0 val_162 +163 163.0 val_163 +164 328.0 val_164 +165 330.0 val_165 +166 166.0 val_166 +167 501.0 val_167 +168 168.0 val_168 +169 676.0 val_169 +17 17.0 val_17 +170 170.0 val_170 +172 344.0 val_172 +174 348.0 val_174 +175 350.0 val_175 +176 352.0 val_176 +177 177.0 val_177 +178 178.0 val_178 +179 358.0 val_179 +18 36.0 val_18 +180 180.0 val_180 +181 181.0 val_181 +183 183.0 val_183 +186 186.0 val_186 +187 561.0 val_187 +189 189.0 val_189 +19 19.0 val_19 +190 190.0 val_190 +191 382.0 val_191 +192 192.0 val_192 +193 579.0 val_193 +194 194.0 val_194 +195 390.0 val_195 +196 196.0 val_196 +197 394.0 val_197 +199 597.0 val_199 +2 2.0 val_2 +20 20.0 val_20 +200 400.0 val_200 +201 201.0 val_201 +202 202.0 val_202 +203 406.0 val_203 +205 410.0 val_205 +207 414.0 val_207 +208 624.0 val_208 +209 418.0 val_209 +213 426.0 val_213 +214 214.0 val_214 +216 432.0 val_216 +217 434.0 val_217 +218 218.0 val_218 +219 438.0 val_219 +221 442.0 val_221 +222 222.0 val_222 +223 446.0 val_223 +224 448.0 val_224 +226 226.0 val_226 +228 228.0 val_228 +229 458.0 val_229 +230 1150.0 val_230 +233 466.0 val_233 +235 235.0 val_235 +237 474.0 val_237 +238 476.0 val_238 +239 478.0 val_239 +24 48.0 val_24 +241 241.0 val_241 +242 484.0 val_242 +244 244.0 val_244 +247 247.0 val_247 +248 248.0 val_248 +249 249.0 val_249 +252 252.0 val_252 +255 510.0 val_255 +256 512.0 val_256 +257 257.0 val_257 +258 258.0 val_258 +26 52.0 val_26 +260 260.0 val_260 +262 262.0 val_262 +263 263.0 val_263 +265 530.0 val_265 +266 266.0 val_266 +27 27.0 val_27 +272 544.0 val_272 +273 819.0 val_273 +274 274.0 val_274 +275 275.0 val_275 +277 1108.0 val_277 +278 556.0 val_278 +28 28.0 val_28 +280 560.0 val_280 +281 562.0 val_281 +282 564.0 val_282 +283 283.0 val_283 +284 284.0 val_284 +285 285.0 val_285 +286 286.0 val_286 +287 287.0 val_287 +288 576.0 val_288 +289 289.0 val_289 +291 291.0 val_291 +292 292.0 val_292 +296 296.0 val_296 +298 894.0 val_298 +30 30.0 val_30 +302 302.0 val_302 +305 305.0 val_305 +306 306.0 val_306 +307 614.0 val_307 +308 308.0 val_308 +309 618.0 val_309 +310 310.0 val_310 +311 933.0 val_311 +315 315.0 val_315 +316 948.0 val_316 +317 634.0 val_317 +318 954.0 val_318 +321 642.0 val_321 +322 644.0 val_322 +323 323.0 val_323 +325 650.0 val_325 +327 981.0 val_327 +33 33.0 val_33 +331 662.0 val_331 +332 332.0 val_332 +333 666.0 val_333 +335 335.0 val_335 +336 336.0 val_336 +338 338.0 val_338 +339 339.0 val_339 +34 34.0 val_34 +341 341.0 val_341 +342 684.0 val_342 +344 688.0 val_344 +345 345.0 val_345 +348 1740.0 val_348 +35 105.0 val_35 +351 351.0 val_351 +353 706.0 val_353 +356 356.0 val_356 +360 360.0 val_360 +362 362.0 val_362 +364 364.0 val_364 +365 365.0 val_365 +366 366.0 val_366 +367 734.0 val_367 +368 368.0 val_368 +369 1107.0 val_369 +37 74.0 val_37 +373 373.0 val_373 +374 374.0 val_374 +375 375.0 val_375 +377 377.0 val_377 +378 378.0 val_378 +379 379.0 val_379 +382 764.0 val_382 +384 1152.0 val_384 +386 386.0 val_386 +389 389.0 val_389 +392 392.0 val_392 +393 393.0 val_393 +394 394.0 val_394 +395 790.0 val_395 +396 1188.0 val_396 +397 794.0 val_397 +399 798.0 val_399 +4 4.0 val_4 +400 400.0 val_400 +401 2005.0 val_401 +402 402.0 val_402 +403 1209.0 val_403 +404 808.0 val_404 +406 1624.0 val_406 +407 407.0 val_407 +409 1227.0 val_409 +41 41.0 val_41 +411 411.0 val_411 +413 826.0 val_413 +414 828.0 val_414 +417 1251.0 val_417 +418 418.0 val_418 +419 419.0 val_419 +42 84.0 val_42 +421 421.0 val_421 +424 848.0 val_424 +427 427.0 val_427 +429 858.0 val_429 +43 43.0 val_43 +430 1290.0 val_430 +431 1293.0 val_431 +432 432.0 val_432 +435 435.0 val_435 +436 436.0 val_436 +437 437.0 val_437 +438 1314.0 val_438 +439 878.0 val_439 +44 44.0 val_44 +443 443.0 val_443 +444 444.0 val_444 +446 446.0 val_446 +448 448.0 val_448 +449 449.0 val_449 +452 452.0 val_452 +453 453.0 val_453 +454 1362.0 val_454 +455 455.0 val_455 +457 457.0 val_457 +458 916.0 val_458 +459 918.0 val_459 +460 460.0 val_460 +462 924.0 val_462 +463 926.0 val_463 +466 1398.0 val_466 +467 467.0 val_467 +468 1872.0 val_468 +469 2345.0 val_469 +47 47.0 val_47 +470 470.0 val_470 +472 472.0 val_472 +475 475.0 val_475 +477 477.0 val_477 +478 956.0 val_478 +479 479.0 val_479 +480 1440.0 val_480 +481 481.0 val_481 +482 482.0 val_482 +483 483.0 val_483 +484 484.0 val_484 +485 485.0 val_485 +487 487.0 val_487 +489 1956.0 val_489 +490 490.0 val_490 +491 491.0 val_491 +492 984.0 val_492 +493 493.0 val_493 +494 494.0 val_494 +495 495.0 val_495 +496 496.0 val_496 +497 497.0 val_497 +498 1494.0 val_498 +5 15.0 val_5 +51 102.0 val_51 +53 53.0 val_53 +54 54.0 val_54 +57 57.0 val_57 +58 116.0 val_58 +64 64.0 val_64 +65 65.0 val_65 +66 66.0 val_66 +67 134.0 val_67 +69 69.0 val_69 +70 210.0 val_70 +72 144.0 val_72 +74 74.0 val_74 +76 152.0 val_76 +77 77.0 val_77 +78 78.0 val_78 +8 8.0 val_8 +80 80.0 val_80 +82 82.0 val_82 +83 166.0 val_83 +84 168.0 val_84 +85 85.0 val_85 +86 86.0 val_86 +87 87.0 val_87 +9 9.0 val_9 +90 270.0 val_90 +92 92.0 val_92 +95 190.0 val_95 +96 96.0 val_96 +97 194.0 val_97 +98 196.0 val_98 +PREHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n2 +PREHOOK: Output: default@e2_n3 +POSTHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n2 +POSTHOOK: Output: default@e2_n3 +POSTHOOK: Lineage: e1_n2.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e1_n2.keyd EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n3.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n3.keyd EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from e1_n2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e1_n2 +#### A masked pattern was here #### +POSTHOOK: query: select * from e1_n2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e1_n2 +#### A masked pattern was here #### +0 1.0 +10 1.0 +100 1.0 +103 1.0 +104 1.0 +105 1.0 +11 1.0 +111 1.0 +113 1.0 +114 1.0 +116 1.0 +118 1.0 +119 1.0 +12 1.0 +120 1.0 +125 1.0 +126 1.0 +128 1.0 +129 1.0 +131 1.0 +133 1.0 +134 1.0 +136 1.0 +137 1.0 +138 1.0 +143 1.0 +145 1.0 +146 1.0 +149 1.0 +15 1.0 +150 1.0 +152 1.0 +153 1.0 +155 1.0 +156 1.0 +157 1.0 +158 1.0 +160 1.0 +162 1.0 +163 1.0 +164 1.0 +165 1.0 +166 1.0 +167 1.0 +168 1.0 +169 1.0 +17 1.0 +170 1.0 +172 1.0 +174 1.0 +175 1.0 +176 1.0 +177 1.0 +178 1.0 +179 1.0 +18 1.0 +180 1.0 +181 1.0 +183 1.0 +186 1.0 +187 1.0 +189 1.0 +19 1.0 +190 1.0 +191 1.0 +192 1.0 +193 1.0 +194 1.0 +195 1.0 +196 1.0 +197 1.0 +199 1.0 +2 1.0 +20 1.0 +200 1.0 +201 1.0 +202 1.0 +203 1.0 +205 1.0 +207 1.0 +208 1.0 +209 1.0 +213 1.0 +214 1.0 +216 1.0 +217 1.0 +218 1.0 +219 1.0 +221 1.0 +222 1.0 +223 1.0 +224 1.0 +226 1.0 +228 1.0 +229 1.0 +230 1.0 +233 1.0 +235 1.0 +237 1.0 +238 1.0 +239 1.0 +24 1.0 +241 1.0 +242 1.0 +244 1.0 +247 1.0 +248 1.0 +249 1.0 +252 1.0 +255 1.0 +256 1.0 +257 1.0 +258 1.0 +26 1.0 +260 1.0 +262 1.0 +263 1.0 +265 1.0 +266 1.0 +27 1.0 +272 1.0 +273 1.0 +274 1.0 +275 1.0 +277 1.0 +278 1.0 +28 1.0 +280 1.0 +281 1.0 +282 1.0 +283 1.0 +284 1.0 +285 1.0 +286 1.0 +287 1.0 +288 1.0 +289 1.0 +291 1.0 +292 1.0 +296 1.0 +298 1.0 +30 1.0 +302 1.0 +305 1.0 +306 1.0 +307 1.0 +308 1.0 +309 1.0 +310 1.0 +311 1.0 +315 1.0 +316 1.0 +317 1.0 +318 1.0 +321 1.0 +322 1.0 +323 1.0 +325 1.0 +327 1.0 +33 1.0 +331 1.0 +332 1.0 +333 1.0 +335 1.0 +336 1.0 +338 1.0 +339 1.0 +34 1.0 +341 1.0 +342 1.0 +344 1.0 +345 1.0 +348 1.0 +35 1.0 +351 1.0 +353 1.0 +356 1.0 +360 1.0 +362 1.0 +364 1.0 +365 1.0 +366 1.0 +367 1.0 +368 1.0 +369 1.0 +37 1.0 +373 1.0 +374 1.0 +375 1.0 +377 1.0 +378 1.0 +379 1.0 +382 1.0 +384 1.0 +386 1.0 +389 1.0 +392 1.0 +393 1.0 +394 1.0 +395 1.0 +396 1.0 +397 1.0 +399 1.0 +4 1.0 +400 1.0 +401 1.0 +402 1.0 +403 1.0 +404 1.0 +406 1.0 +407 1.0 +409 1.0 +41 1.0 +411 1.0 +413 1.0 +414 1.0 +417 1.0 +418 1.0 +419 1.0 +42 1.0 +421 1.0 +424 1.0 +427 1.0 +429 1.0 +43 1.0 +430 1.0 +431 1.0 +432 1.0 +435 1.0 +436 1.0 +437 1.0 +438 1.0 +439 1.0 +44 1.0 +443 1.0 +444 1.0 +446 1.0 +448 1.0 +449 1.0 +452 1.0 +453 1.0 +454 1.0 +455 1.0 +457 1.0 +458 1.0 +459 1.0 +460 1.0 +462 1.0 +463 1.0 +466 1.0 +467 1.0 +468 1.0 +469 1.0 +47 1.0 +470 1.0 +472 1.0 +475 1.0 +477 1.0 +478 1.0 +479 1.0 +480 1.0 +481 1.0 +482 1.0 +483 1.0 +484 1.0 +485 1.0 +487 1.0 +489 1.0 +490 1.0 +491 1.0 +492 1.0 +493 1.0 +494 1.0 +495 1.0 +496 1.0 +497 1.0 +498 1.0 +5 1.0 +51 1.0 +53 1.0 +54 1.0 +57 1.0 +58 1.0 +64 1.0 +65 1.0 +66 1.0 +67 1.0 +69 1.0 +70 1.0 +72 1.0 +74 1.0 +76 1.0 +77 1.0 +78 1.0 +8 1.0 +80 1.0 +82 1.0 +83 1.0 +84 1.0 +85 1.0 +86 1.0 +87 1.0 +9 1.0 +90 1.0 +92 1.0 +95 1.0 +96 1.0 +97 1.0 +98 1.0 +PREHOOK: query: select * from e2_n3 +PREHOOK: type: QUERY +PREHOOK: Input: default@e2_n3 +#### A masked pattern was here #### +POSTHOOK: query: select * from e2_n3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e2_n3 +#### A masked pattern was here #### +0 0.0 val_0 +10 10.0 val_10 +100 200.0 val_100 +103 206.0 val_103 +104 208.0 val_104 +105 105.0 val_105 +11 11.0 val_11 +111 111.0 val_111 +113 226.0 val_113 +114 114.0 val_114 +116 116.0 val_116 +118 236.0 val_118 +119 357.0 val_119 +12 24.0 val_12 +120 240.0 val_120 +125 250.0 val_125 +126 126.0 val_126 +128 384.0 val_128 +129 258.0 val_129 +131 131.0 val_131 +133 133.0 val_133 +134 268.0 val_134 +136 136.0 val_136 +137 274.0 val_137 +138 552.0 val_138 +143 143.0 val_143 +145 145.0 val_145 +146 292.0 val_146 +149 298.0 val_149 +15 30.0 val_15 +150 150.0 val_150 +152 304.0 val_152 +153 153.0 val_153 +155 155.0 val_155 +156 156.0 val_156 +157 157.0 val_157 +158 158.0 val_158 +160 160.0 val_160 +162 162.0 val_162 +163 163.0 val_163 +164 328.0 val_164 +165 330.0 val_165 +166 166.0 val_166 +167 501.0 val_167 +168 168.0 val_168 +169 676.0 val_169 +17 17.0 val_17 +170 170.0 val_170 +172 344.0 val_172 +174 348.0 val_174 +175 350.0 val_175 +176 352.0 val_176 +177 177.0 val_177 +178 178.0 val_178 +179 358.0 val_179 +18 36.0 val_18 +180 180.0 val_180 +181 181.0 val_181 +183 183.0 val_183 +186 186.0 val_186 +187 561.0 val_187 +189 189.0 val_189 +19 19.0 val_19 +190 190.0 val_190 +191 382.0 val_191 +192 192.0 val_192 +193 579.0 val_193 +194 194.0 val_194 +195 390.0 val_195 +196 196.0 val_196 +197 394.0 val_197 +199 597.0 val_199 +2 2.0 val_2 +20 20.0 val_20 +200 400.0 val_200 +201 201.0 val_201 +202 202.0 val_202 +203 406.0 val_203 +205 410.0 val_205 +207 414.0 val_207 +208 624.0 val_208 +209 418.0 val_209 +213 426.0 val_213 +214 214.0 val_214 +216 432.0 val_216 +217 434.0 val_217 +218 218.0 val_218 +219 438.0 val_219 +221 442.0 val_221 +222 222.0 val_222 +223 446.0 val_223 +224 448.0 val_224 +226 226.0 val_226 +228 228.0 val_228 +229 458.0 val_229 +230 1150.0 val_230 +233 466.0 val_233 +235 235.0 val_235 +237 474.0 val_237 +238 476.0 val_238 +239 478.0 val_239 +24 48.0 val_24 +241 241.0 val_241 +242 484.0 val_242 +244 244.0 val_244 +247 247.0 val_247 +248 248.0 val_248 +249 249.0 val_249 +252 252.0 val_252 +255 510.0 val_255 +256 512.0 val_256 +257 257.0 val_257 +258 258.0 val_258 +26 52.0 val_26 +260 260.0 val_260 +262 262.0 val_262 +263 263.0 val_263 +265 530.0 val_265 +266 266.0 val_266 +27 27.0 val_27 +272 544.0 val_272 +273 819.0 val_273 +274 274.0 val_274 +275 275.0 val_275 +277 1108.0 val_277 +278 556.0 val_278 +28 28.0 val_28 +280 560.0 val_280 +281 562.0 val_281 +282 564.0 val_282 +283 283.0 val_283 +284 284.0 val_284 +285 285.0 val_285 +286 286.0 val_286 +287 287.0 val_287 +288 576.0 val_288 +289 289.0 val_289 +291 291.0 val_291 +292 292.0 val_292 +296 296.0 val_296 +298 894.0 val_298 +30 30.0 val_30 +302 302.0 val_302 +305 305.0 val_305 +306 306.0 val_306 +307 614.0 val_307 +308 308.0 val_308 +309 618.0 val_309 +310 310.0 val_310 +311 933.0 val_311 +315 315.0 val_315 +316 948.0 val_316 +317 634.0 val_317 +318 954.0 val_318 +321 642.0 val_321 +322 644.0 val_322 +323 323.0 val_323 +325 650.0 val_325 +327 981.0 val_327 +33 33.0 val_33 +331 662.0 val_331 +332 332.0 val_332 +333 666.0 val_333 +335 335.0 val_335 +336 336.0 val_336 +338 338.0 val_338 +339 339.0 val_339 +34 34.0 val_34 +341 341.0 val_341 +342 684.0 val_342 +344 688.0 val_344 +345 345.0 val_345 +348 1740.0 val_348 +35 105.0 val_35 +351 351.0 val_351 +353 706.0 val_353 +356 356.0 val_356 +360 360.0 val_360 +362 362.0 val_362 +364 364.0 val_364 +365 365.0 val_365 +366 366.0 val_366 +367 734.0 val_367 +368 368.0 val_368 +369 1107.0 val_369 +37 74.0 val_37 +373 373.0 val_373 +374 374.0 val_374 +375 375.0 val_375 +377 377.0 val_377 +378 378.0 val_378 +379 379.0 val_379 +382 764.0 val_382 +384 1152.0 val_384 +386 386.0 val_386 +389 389.0 val_389 +392 392.0 val_392 +393 393.0 val_393 +394 394.0 val_394 +395 790.0 val_395 +396 1188.0 val_396 +397 794.0 val_397 +399 798.0 val_399 +4 4.0 val_4 +400 400.0 val_400 +401 2005.0 val_401 +402 402.0 val_402 +403 1209.0 val_403 +404 808.0 val_404 +406 1624.0 val_406 +407 407.0 val_407 +409 1227.0 val_409 +41 41.0 val_41 +411 411.0 val_411 +413 826.0 val_413 +414 828.0 val_414 +417 1251.0 val_417 +418 418.0 val_418 +419 419.0 val_419 +42 84.0 val_42 +421 421.0 val_421 +424 848.0 val_424 +427 427.0 val_427 +429 858.0 val_429 +43 43.0 val_43 +430 1290.0 val_430 +431 1293.0 val_431 +432 432.0 val_432 +435 435.0 val_435 +436 436.0 val_436 +437 437.0 val_437 +438 1314.0 val_438 +439 878.0 val_439 +44 44.0 val_44 +443 443.0 val_443 +444 444.0 val_444 +446 446.0 val_446 +448 448.0 val_448 +449 449.0 val_449 +452 452.0 val_452 +453 453.0 val_453 +454 1362.0 val_454 +455 455.0 val_455 +457 457.0 val_457 +458 916.0 val_458 +459 918.0 val_459 +460 460.0 val_460 +462 924.0 val_462 +463 926.0 val_463 +466 1398.0 val_466 +467 467.0 val_467 +468 1872.0 val_468 +469 2345.0 val_469 +47 47.0 val_47 +470 470.0 val_470 +472 472.0 val_472 +475 475.0 val_475 +477 477.0 val_477 +478 956.0 val_478 +479 479.0 val_479 +480 1440.0 val_480 +481 481.0 val_481 +482 482.0 val_482 +483 483.0 val_483 +484 484.0 val_484 +485 485.0 val_485 +487 487.0 val_487 +489 1956.0 val_489 +490 490.0 val_490 +491 491.0 val_491 +492 984.0 val_492 +493 493.0 val_493 +494 494.0 val_494 +495 495.0 val_495 +496 496.0 val_496 +497 497.0 val_497 +498 1494.0 val_498 +5 15.0 val_5 +51 102.0 val_51 +53 53.0 val_53 +54 54.0 val_54 +57 57.0 val_57 +58 116.0 val_58 +64 64.0 val_64 +65 65.0 val_65 +66 66.0 val_66 +67 134.0 val_67 +69 69.0 val_69 +70 210.0 val_70 +72 144.0 val_72 +74 74.0 val_74 +76 152.0 val_76 +77 77.0 val_77 +78 78.0 val_78 +8 8.0 val_8 +80 80.0 val_80 +82 82.0 val_82 +83 166.0 val_83 +84 168.0 val_84 +85 85.0 val_85 +86 86.0 val_86 +87 87.0 val_87 +9 9.0 val_9 +90 270.0 val_90 +92 92.0 val_92 +95 190.0 val_95 +96 96.0 val_96 +97 194.0 val_97 +98 196.0 val_98 +PREHOOK: query: explain +from src +insert overwrite table e1_n2 +select key, count(distinct value) group by key +insert overwrite table e3 +select value, count(distinct key) group by value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n2 +PREHOOK: Output: default@e3 +POSTHOOK: query: explain +from src +insert overwrite table e1_n2 +select key, count(distinct value) group by key +insert overwrite table e3 +select value, count(distinct key) group by value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n2 +POSTHOOK: Output: default@e3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT value) + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT key) + keys: value (type: string), key (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: key, keyd + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e3 + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: key, keyd + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd + Column Types: string, double + Table: default.e1_n2 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd + Column Types: string, double + Table: default.e3 + +PREHOOK: query: explain +FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +INSERT overwrite table e3 + SELECT key, COUNT(distinct keyD) group by key, keyD, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n2 +PREHOOK: Output: default@e2_n3 +PREHOOK: Output: default@e3 +POSTHOOK: query: explain +FROM (select key, cast(key as double) as keyD, value from src order by key) a +INSERT OVERWRITE TABLE e1_n2 + SELECT key, COUNT(distinct value) group by key +INSERT OVERWRITE TABLE e2_n3 + SELECT key, sum(keyD), value group by key, value +INSERT overwrite table e3 + SELECT key, COUNT(distinct keyD) group by key, keyD, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n2 +POSTHOOK: Output: default@e2_n3 +POSTHOOK: Output: default@e3 +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-4 + Stage-7 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-3 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) + Reducer 6 <- Map 1 (SIMPLE_EDGE) + Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(DISTINCT _col2) + keys: _col0 (type: string), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: double) + Group By Operator + aggregations: count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: double), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) + null sort order: zzzz + sort order: ++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: string) + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col1:0._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: key, keyd + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n3 + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) + outputColumnNames: key, keyd, value + Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(DISTINCT KEY._col3:0._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col3) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e3 + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: key, keyd + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-4 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n2 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd + Column Types: string, double + Table: default.e1_n2 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n3 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd, value + Column Types: string, double, string + Table: default.e2_n3 + + Stage: Stage-2 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e3 + + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, keyd + Column Types: string, double + Table: default.e3 + diff --git ql/src/test/results/clientpositive/llap/multi_insert_gby4.q.out ql/src/test/results/clientpositive/llap/multi_insert_gby4.q.out new file mode 100644 index 0000000000..554a174f5c --- /dev/null +++ ql/src/test/results/clientpositive/llap/multi_insert_gby4.q.out @@ -0,0 +1,406 @@ +PREHOOK: query: create table e1_n4 (key string, count int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e1_n4 +POSTHOOK: query: create table e1_n4 (key string, count int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e1_n4 +PREHOOK: query: create table e2_n5 (key string, count int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e2_n5 +POSTHOOK: query: create table e2_n5 (key string, count int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e2_n5 +PREHOOK: query: create table e3_n0 (key string, count int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e3_n0 +POSTHOOK: query: create table e3_n0 (key string, count int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e3_n0 +PREHOOK: query: explain +FROM (SELECT key, value FROM src) a +INSERT OVERWRITE TABLE e1_n4 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n5 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +INSERT OVERWRITE TABLE e3_n0 + SELECT key, COUNT(*) WHERE key>490 GROUP BY key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n4 +PREHOOK: Output: default@e2_n5 +PREHOOK: Output: default@e3_n0 +POSTHOOK: query: explain +FROM (SELECT key, value FROM src) a +INSERT OVERWRITE TABLE e1_n4 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n5 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +INSERT OVERWRITE TABLE e3_n0 + SELECT key, COUNT(*) WHERE key>490 GROUP BY key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n4 +POSTHOOK: Output: default@e2_n5 +POSTHOOK: Output: default@e3_n0 +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-4 + Stage-7 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-3 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col0 > 490) or ((_col0 > 500) or (_col0 > 450))) (type: boolean) + Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 > 450) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, count + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (KEY._col0 > 500) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, count + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (KEY._col0 > 490) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e3_n0 + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: key, count + Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-4 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e1_n4 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, count + Column Types: string, int + Table: default.e1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e2_n5 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, count + Column Types: string, int + Table: default.e2_n5 + + Stage: Stage-2 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.e3_n0 + + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, count + Column Types: string, int + Table: default.e3_n0 + +PREHOOK: query: FROM (SELECT key, value FROM src) a +INSERT OVERWRITE TABLE e1_n4 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n5 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +INSERT OVERWRITE TABLE e3_n0 + SELECT key, COUNT(*) WHERE key>490 GROUP BY key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@e1_n4 +PREHOOK: Output: default@e2_n5 +PREHOOK: Output: default@e3_n0 +POSTHOOK: query: FROM (SELECT key, value FROM src) a +INSERT OVERWRITE TABLE e1_n4 + SELECT key, COUNT(*) WHERE key>450 GROUP BY key +INSERT OVERWRITE TABLE e2_n5 + SELECT key, COUNT(*) WHERE key>500 GROUP BY key +INSERT OVERWRITE TABLE e3_n0 + SELECT key, COUNT(*) WHERE key>490 GROUP BY key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@e1_n4 +POSTHOOK: Output: default@e2_n5 +POSTHOOK: Output: default@e3_n0 +POSTHOOK: Lineage: e1_n4.count EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: e1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e2_n5.count EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: e2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: e3_n0.count EXPRESSION [(src)src.null, ] +POSTHOOK: Lineage: e3_n0.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +PREHOOK: query: select * from e1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@e1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from e1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e1_n4 +#### A masked pattern was here #### +452 1 +453 1 +454 3 +455 1 +457 1 +458 2 +459 2 +460 1 +462 2 +463 2 +466 3 +467 1 +468 4 +469 5 +470 1 +472 1 +475 1 +477 1 +478 2 +479 1 +480 3 +481 1 +482 1 +483 1 +484 1 +485 1 +487 1 +489 4 +490 1 +491 1 +492 2 +493 1 +494 1 +495 1 +496 1 +497 1 +498 3 +PREHOOK: query: select * from e2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@e2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from e2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e2_n5 +#### A masked pattern was here #### +PREHOOK: query: select * from e3_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@e3_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * from e3_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e3_n0 +#### A masked pattern was here #### +491 1 +492 2 +493 1 +494 1 +495 1 +496 1 +497 1 +498 3 diff --git ql/src/test/results/clientpositive/multi_insert_mixed.q.out ql/src/test/results/clientpositive/llap/multi_insert_mixed.q.out similarity index 58% rename from ql/src/test/results/clientpositive/multi_insert_mixed.q.out rename to ql/src/test/results/clientpositive/llap/multi_insert_mixed.q.out index b7b721e500..2bbf32e0a3 100644 --- ql/src/test/results/clientpositive/multi_insert_mixed.q.out +++ ql/src/test/results/clientpositive/llap/multi_insert_mixed.q.out @@ -46,137 +46,195 @@ STAGE DEPENDENCIES: Stage-3 is a root stage Stage-4 depends on stages: Stage-3 Stage-0 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-0, Stage-10 - Stage-6 depends on stages: Stage-3 - Stage-7 depends on stages: Stage-6 - Stage-1 depends on stages: Stage-7 - Stage-8 depends on stages: Stage-1, Stage-10 - Stage-2 depends on stages: Stage-3 - Stage-9 depends on stages: Stage-2, Stage-10 - Stage-10 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-4 + Stage-7 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 6 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count(1) - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + - Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), CAST( VALUE._col0 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n2 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: Select Operator - expressions: key (type: string), value (type: string) + expressions: KEY.reducesinkkey0 (type: string), CAST( VALUE._col0 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi3 + name: default.src_multi2_n3 Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash + mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), CAST( VALUE._col0 AS STRING) (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n2 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: struct), _col1 (type: struct) + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -187,6 +245,9 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-4 + Dependency Collection + Stage: Stage-0 Move Operator tables: @@ -205,77 +266,6 @@ STAGE PLANS: Column Types: string, string Table: default.src_multi1_n2 - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), CAST( VALUE._col0 AS STRING) (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 250 Data size: 68750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: struct), _col1 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-1 Move Operator tables: @@ -286,7 +276,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src_multi2_n3 - Stage: Stage-8 + Stage: Stage-6 Stats Work Basic Stats Work: Column Stats Desc: @@ -304,7 +294,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src_multi3 - Stage: Stage-9 + Stage: Stage-7 Stats Work Basic Stats Work: Column Stats Desc: @@ -312,30 +302,6 @@ STAGE PLANS: Column Types: string, string Table: default.src_multi3 - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - PREHOOK: query: from src insert overwrite table src_multi1_n2 select key, count(1) group by key order by key insert overwrite table src_multi2_n3 select value, count(1) group by value order by value diff --git ql/src/test/results/clientpositive/llap/multi_insert_move_tasks_share_dependencies.q.out ql/src/test/results/clientpositive/llap/multi_insert_move_tasks_share_dependencies.q.out new file mode 100644 index 0000000000..8a042db312 --- /dev/null +++ ql/src/test/results/clientpositive/llap/multi_insert_move_tasks_share_dependencies.q.out @@ -0,0 +1,5229 @@ +PREHOOK: query: create table src_multi1_n4 like src +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src_multi1_n4 +POSTHOOK: query: create table src_multi1_n4 like src +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_multi1_n4 +PREHOOK: query: create table src_multi2_n5 like src +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: create table src_multi2_n5 like src +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_multi2_n5 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.98630136 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9583333 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +2 val_2 +4 val_4 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +15 val_15 +17 val_17 +18 val_18 +19 val_19 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.98630136 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9583333 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +2 val_2 +4 val_4 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +15 val_15 +17 val_17 +18 val_18 +19 val_19 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.98630136 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9583333 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +2 val_2 +4 val_4 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +15 val_15 +17 val_17 +18 val_18 +19 val_19 +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.98630136 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9583333 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 group by key, value +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +2 val_2 +4 val_4 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +15 val_15 +17 val_17 +18 val_18 +19 val_19 +PREHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 5 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Union 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union 2 + Vertex: Union 2 + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +2 val_2 +4 val_4 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +8 val_8 +9 val_9 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +11 val_11 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +17 val_17 +17 val_17 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +19 val_19 +19 val_19 +PREHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 5 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Union 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union 2 + Vertex: Union 2 + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +2 val_2 +4 val_4 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +8 val_8 +9 val_9 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +11 val_11 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +17 val_17 +17 val_17 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +19 val_19 +19 val_19 +PREHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 5 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Union 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union 2 + Vertex: Union 2 + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +2 val_2 +4 val_4 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +8 val_8 +9 val_9 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +11 val_11 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +17 val_17 +17 val_17 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +19 val_19 +19 val_19 +PREHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 5 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Union 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 10) (type: boolean) + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union 2 + Vertex: Union 2 + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + +PREHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from (select * from src union all select * from src) s +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +2 val_2 +4 val_4 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +8 val_8 +9 val_9 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +11 val_11 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +17 val_17 +17 val_17 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +19 val_19 +19 val_19 +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-3 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 2) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 4) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-4 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-3 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 2) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 4) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-4 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-3 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 2) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 4) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-4 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-3 + Stage-2 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-3 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 2) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: (key = 4) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-4 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-1 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: from src +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0, Stage-2, Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-1, Stage-2, Stage-3 + Stage-2 depends on stages: Stage-4 + Stage-3 depends on stages: Stage-4 + +STAGE PLANS: + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-3 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0, Stage-2, Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-1, Stage-2, Stage-3 + Stage-2 depends on stages: Stage-4 + Stage-3 depends on stages: Stage-4 + +STAGE PLANS: + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-3 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0, Stage-2, Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-1, Stage-2, Stage-3 + Stage-2 depends on stages: Stage-4 + Stage-3 depends on stages: Stage-4 + +STAGE PLANS: + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-3 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +Found 2 items +#### A masked pattern was here #### +PREHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: explain +from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0, Stage-2, Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-1, Stage-2, Stage-3 + Stage-2 depends on stages: Stage-4 + Stage-3 depends on stages: Stage-4 + +STAGE PLANS: + Stage: Stage-4 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key < 10) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((key > 10) and (key < 20)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (KEY._col0 < 10) (type: boolean) + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n4 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi1_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n5 + + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_multi2_n5 + + Stage: Stage-2 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + + Stage: Stage-3 + Move Operator + files: + hdfs directory: false +#### A masked pattern was here #### + +PREHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: Output: default@src_multi1_n4 +PREHOOK: Output: default@src_multi2_n5 +POSTHOOK: query: from src +insert overwrite table src_multi1_n4 select * where key < 10 +insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 +#### A masked pattern was here #### +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: Output: default@src_multi1_n4 +POSTHOOK: Output: default@src_multi2_n5 +POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from src_multi1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi1_n4 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +PREHOOK: query: select * from src_multi2_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_multi2_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_multi2_n5 +#### A masked pattern was here #### +11 val_11 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +17 val_17 +18 val_18 +18 val_18 +19 val_19 +Found 2 items +#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/multi_insert_union_src.q.out ql/src/test/results/clientpositive/llap/multi_insert_union_src.q.out similarity index 56% rename from ql/src/test/results/clientpositive/multi_insert_union_src.q.out rename to ql/src/test/results/clientpositive/llap/multi_insert_union_src.q.out index 90597f37d9..335af8f9c6 100644 --- ql/src/test/results/clientpositive/multi_insert_union_src.q.out +++ ql/src/test/results/clientpositive/llap/multi_insert_union_src.q.out @@ -58,111 +58,156 @@ POSTHOOK: Output: default@src_multi1_n3 POSTHOOK: Output: default@src_multi2_n4 STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 Stage-5 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 174 Data size: 30948 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 5 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (SIMPLE_EDGE) + Reducer 4 <- Union 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col0 < 150) (type: boolean) - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + predicate: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 1400 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 150) (type: boolean) + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Filter Operator + predicate: (_col0 > 400) (type: boolean) + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src2_n4 + filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (_col0 > 400) (type: boolean) - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: src2_n4 - filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (UDFToDouble(key) > 100.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 150) (type: boolean) + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Filter Operator + predicate: (_col0 > 400) (type: boolean) + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator - expressions: key (type: string), value (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 174 Data size: 30948 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 150) (type: boolean) - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Filter Operator - predicate: (_col0 > 400) (type: boolean) - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi1_n3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: Select Operator - expressions: _col0 (type: struct), _col1 (type: struct) + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_multi2_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union 2 + Vertex: Union 2 + + Stage: Stage-3 + Dependency Collection Stage: Stage-0 Move Operator @@ -174,7 +219,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src_multi1_n3 - Stage: Stage-3 + Stage: Stage-4 Stats Work Basic Stats Work: Column Stats Desc: @@ -182,51 +227,6 @@ STAGE PLANS: Column Types: string, string Table: default.src_multi1_n3 - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 58 Data size: 10324 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: struct), _col1 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-1 Move Operator tables: diff --git ql/src/test/results/clientpositive/llap/multi_insert_with_join2.q.out ql/src/test/results/clientpositive/llap/multi_insert_with_join2.q.out new file mode 100644 index 0000000000..4af33dcfe8 --- /dev/null +++ ql/src/test/results/clientpositive/llap/multi_insert_with_join2.q.out @@ -0,0 +1,1682 @@ +PREHOOK: query: CREATE TABLE T_A ( id STRING, val STRING ) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T_A +POSTHOOK: query: CREATE TABLE T_A ( id STRING, val STRING ) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T_A +PREHOOK: query: CREATE TABLE T_B ( id STRING, val STRING ) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T_B +POSTHOOK: query: CREATE TABLE T_B ( id STRING, val STRING ) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T_B +PREHOOK: query: CREATE TABLE join_result_1 ( ida STRING, vala STRING, idb STRING, valb STRING ) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@join_result_1 +POSTHOOK: query: CREATE TABLE join_result_1 ( ida STRING, vala STRING, idb STRING, valb STRING ) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@join_result_1 +PREHOOK: query: CREATE TABLE join_result_3 ( ida STRING, vala STRING, idb STRING, valb STRING ) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: CREATE TABLE join_result_3 ( ida STRING, vala STRING, idb STRING, valb STRING ) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@join_result_3 +PREHOOK: query: INSERT INTO TABLE T_A +VALUES ('Id_1', 'val_101'), ('Id_2', 'val_102'), ('Id_3', 'val_103') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t_a +POSTHOOK: query: INSERT INTO TABLE T_A +VALUES ('Id_1', 'val_101'), ('Id_2', 'val_102'), ('Id_3', 'val_103') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t_a +POSTHOOK: Lineage: t_a.id SCRIPT [] +POSTHOOK: Lineage: t_a.val SCRIPT [] +PREHOOK: query: INSERT INTO TABLE T_B +VALUES ('Id_1', 'val_103'), ('Id_2', 'val_104') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t_b +POSTHOOK: query: INSERT INTO TABLE T_B +VALUES ('Id_1', 'val_103'), ('Id_2', 'val_104') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t_b +POSTHOOK: Lineage: t_b.id SCRIPT [] +POSTHOOK: Lineage: t_b.val SCRIPT [] +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_1 +POSTHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_1 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (id = 'Id_1') (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (id = 'Id_1') (type: boolean) + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: val (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'Id_1' (type: string), _col0 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_1 + +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_3 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: val (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((id = 'Id_2') and (val = 'val_104')) (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((id = 'Id_2') and (val = 'val_104')) (type: boolean) + Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'Id_2' (type: string), _col0 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_3 + +PREHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_1 +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_1 +POSTHOOK: Output: default@join_result_3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 id (type: string) + 1 id (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2') and (_col1 <> _col6)) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Filter Operator + predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_3 + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_1 + +PREHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_1 +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: explain +FROM T_A a LEFT JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_1 +POSTHOOK: Output: default@join_result_3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 id (type: string) + 1 id (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Filter Operator + predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_1 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_3 + +PREHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_1 +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.*, b.* +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.*, b.* +WHERE b.val = 'val_104' AND b.id = 'Id_2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_1 +POSTHOOK: Output: default@join_result_3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 id (type: string) + 1 id (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Filter Operator + predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_1 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_3 + +PREHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT * +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT * +WHERE b.val = 'val_104' AND b.id = 'Id_2' +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_1 +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT * +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT * +WHERE b.val = 'val_104' AND b.id = 'Id_2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_1 +POSTHOOK: Output: default@join_result_3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: id (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: id (type: string) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: val (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 id (type: string) + 1 id (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Filter Operator + predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_1 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_3 + +PREHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.id, a.val, b.id, b.val +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.id, a.val, b.id, b.val +WHERE b.val = 'val_104' AND b.id = 'Id_2' +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_1 +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.id, a.val, b.id, b.val +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.id, a.val, b.id, b.val +WHERE b.val = 'val_104' AND b.id = 'Id_2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_1 +POSTHOOK: Output: default@join_result_3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col3 = 'Id_1') and (_col2 = 'val_103')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Filter Operator + predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_1 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_3 + +PREHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.val, a.id, b.id, b.val +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.id, b.val, b.id, a.val +WHERE b.val = 'val_104' AND b.id = 'Id_2' +PREHOOK: type: QUERY +PREHOOK: Input: default@t_a +PREHOOK: Input: default@t_b +PREHOOK: Output: default@join_result_1 +PREHOOK: Output: default@join_result_3 +POSTHOOK: query: explain +FROM T_A a JOIN T_B b ON a.id = b.id +INSERT OVERWRITE TABLE join_result_1 +SELECT a.val, a.id, b.id, b.val +WHERE b.id = 'Id_1' AND b.val = 'val_103' +INSERT OVERWRITE TABLE join_result_3 +SELECT a.id, b.val, b.id, a.val +WHERE b.val = 'val_104' AND b.id = 'Id_2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t_a +POSTHOOK: Input: default@t_b +POSTHOOK: Output: default@join_result_1 +POSTHOOK: Output: default@join_result_3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: id is not null (type: boolean) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col3 = 'Id_1') and (_col2 = 'val_103')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Filter Operator + predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: ida, vala, idb, valb + Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_1 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_1 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.join_result_3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: ida, vala, idb, valb + Column Types: string, string, string, string + Table: default.join_result_3 + diff --git ql/src/test/results/clientpositive/llap/multi_join_union.q.out ql/src/test/results/clientpositive/llap/multi_join_union.q.out new file mode 100644 index 0000000000..f59af26fd7 --- /dev/null +++ ql/src/test/results/clientpositive/llap/multi_join_union.q.out @@ -0,0 +1,216 @@ +PREHOOK: query: CREATE TABLE src11 as SELECT * FROM src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@src11 +POSTHOOK: query: CREATE TABLE src11 as SELECT * FROM src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src11 +POSTHOOK: Lineage: src11.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src11.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: CREATE TABLE src12 as SELECT * FROM src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@src12 +POSTHOOK: query: CREATE TABLE src12 as SELECT * FROM src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src12 +POSTHOOK: Lineage: src12.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src12.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: CREATE TABLE src13 as SELECT * FROM src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@src13 +POSTHOOK: query: CREATE TABLE src13 as SELECT * FROM src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src13 +POSTHOOK: Lineage: src13.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src13.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: CREATE TABLE src14 as SELECT * FROM src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@src14 +POSTHOOK: query: CREATE TABLE src14 as SELECT * FROM src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src14 +POSTHOOK: Lineage: src14.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src14.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: EXPLAIN SELECT * FROM +src11 a JOIN +src12 b ON (a.key = b.key) JOIN +(SELECT * FROM (SELECT * FROM src13 UNION ALL SELECT * FROM src14)a )c ON c.value = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src11 +PREHOOK: Input: default@src12 +PREHOOK: Input: default@src13 +PREHOOK: Input: default@src14 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM +src11 a JOIN +src12 b ON (a.key = b.key) JOIN +(SELECT * FROM (SELECT * FROM src13 UNION ALL SELECT * FROM src14)a )c ON c.value = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src11 +POSTHOOK: Input: default@src12 +POSTHOOK: Input: default@src13 +POSTHOOK: Input: default@src14 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) + Map 3 <- Map 1 (BROADCAST_EDGE), Union 4 (CONTAINS) + Map 5 <- Map 1 (BROADCAST_EDGE), Union 4 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Reduce Output Operator + key expressions: _col3 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src13 + filterExpr: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + input vertices: + 0 Map 1 + Statistics: Num rows: 2576 Data size: 1375584 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2576 Data size: 1375584 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src14 + filterExpr: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + input vertices: + 0 Map 1 + Statistics: Num rows: 2576 Data size: 1375584 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2576 Data size: 1375584 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Union 4 + Vertex: Union 4 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/multigroupby_singlemr.q.out ql/src/test/results/clientpositive/llap/multigroupby_singlemr.q.out new file mode 100644 index 0000000000..998772752c --- /dev/null +++ ql/src/test/results/clientpositive/llap/multigroupby_singlemr.q.out @@ -0,0 +1,1208 @@ +PREHOOK: query: CREATE TABLE TBL_n0(C1 INT, C2 INT, C3 INT, C4 INT) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@TBL_n0 +POSTHOOK: query: CREATE TABLE TBL_n0(C1 INT, C2 INT, C3 INT, C4 INT) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@TBL_n0 +PREHOOK: query: CREATE TABLE DEST1_n116(d1 INT, d2 INT) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@DEST1_n116 +POSTHOOK: query: CREATE TABLE DEST1_n116(d1 INT, d2 INT) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@DEST1_n116 +PREHOOK: query: CREATE TABLE DEST2_n30(d1 INT, d2 INT, d3 INT) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@DEST2_n30 +POSTHOOK: query: CREATE TABLE DEST2_n30(d1 INT, d2 INT, d3 INT) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@DEST2_n30 +PREHOOK: query: CREATE TABLE DEST3_n4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@DEST3_n4 +POSTHOOK: query: CREATE TABLE DEST3_n4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@DEST3_n4 +PREHOOK: query: CREATE TABLE DEST4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@DEST4 +POSTHOOK: query: CREATE TABLE DEST4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@DEST4 +PREHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_n0 +PREHOOK: Output: default@dest1_n116 +PREHOOK: Output: default@dest2_n30 +POSTHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_n0 +POSTHOOK: Output: default@dest1_n116 +POSTHOOK: Output: default@dest2_n30 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl_n0 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c1 (type: int), c2 (type: int) + outputColumnNames: c1, c2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c2) + keys: c1 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Select Operator + expressions: c1 (type: int), c2 (type: int), c3 (type: int) + outputColumnNames: c1, c2, c3 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c3) + keys: c1 (type: int), c2 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n116 + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: d1, d2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: d1, d2, d3 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n116 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2 + Column Types: int, int + Table: default.dest1_n116 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3 + Column Types: int, int, int + Table: default.dest2_n30 + +PREHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C2, TBL_n0.C1 +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_n0 +PREHOOK: Output: default@dest1_n116 +PREHOOK: Output: default@dest2_n30 +POSTHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C2, TBL_n0.C1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_n0 +POSTHOOK: Output: default@dest1_n116 +POSTHOOK: Output: default@dest2_n30 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl_n0 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c1 (type: int), c2 (type: int) + outputColumnNames: c1, c2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c2) + keys: c1 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Select Operator + expressions: c1 (type: int), c2 (type: int), c3 (type: int) + outputColumnNames: c1, c2, c3 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c3) + keys: c2 (type: int), c1 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n116 + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: d1, d2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col0 (type: int), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: d1, d2, d3 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n116 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2 + Column Types: int, int + Table: default.dest1_n116 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3 + Column Types: int, int, int + Table: default.dest2_n30 + +PREHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_n0 +PREHOOK: Output: default@dest2_n30 +PREHOOK: Output: default@dest3_n4 +POSTHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_n0 +POSTHOOK: Output: default@dest2_n30 +POSTHOOK: Output: default@dest3_n4 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl_n0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) + outputColumnNames: c1, c2, c3, c4 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c4) + keys: c1 (type: int), c2 (type: int), c3 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Select Operator + expressions: c1 (type: int), c2 (type: int), c3 (type: int) + outputColumnNames: c1, c2, c3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c3) + keys: c1 (type: int), c2 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest3_n4 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) + outputColumnNames: d1, d2, d3, d4 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: d1, d2, d3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest3_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3, d4 + Column Types: int, int, int, int + Table: default.dest3_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3 + Column Types: int, int, int + Table: default.dest2_n30 + +PREHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 +INSERT OVERWRITE TABLE DEST4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C3, TBL_n0.C2 +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_n0 +PREHOOK: Output: default@dest3_n4 +PREHOOK: Output: default@dest4 +POSTHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 +INSERT OVERWRITE TABLE DEST4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C3, TBL_n0.C2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_n0 +POSTHOOK: Output: default@dest3_n4 +POSTHOOK: Output: default@dest4 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl_n0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) + outputColumnNames: c1, c2, c3, c4 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: c1 (type: int), c2 (type: int), c3 (type: int) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: c1 (type: int), c2 (type: int), c3 (type: int) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: c4 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Forward + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest3_n4 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) + outputColumnNames: d1, d2, d3, d4 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col2 (type: int), KEY._col1 (type: int) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), UDFToInteger(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest4 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) + outputColumnNames: d1, d2, d3, d4 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest3_n4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3, d4 + Column Types: int, int, int, int + Table: default.dest3_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest4 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3, d4 + Column Types: int, int, int, int + Table: default.dest4 + +PREHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 +INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_n0 +PREHOOK: Output: default@dest1_n116 +PREHOOK: Output: default@dest2_n30 +PREHOOK: Output: default@dest3_n4 +POSTHOOK: query: EXPLAIN +FROM TBL_n0 +INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 +INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 +INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_n0 +POSTHOOK: Output: default@dest1_n116 +POSTHOOK: Output: default@dest2_n30 +POSTHOOK: Output: default@dest3_n4 +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-4 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-4 + Stage-6 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-4 + Stage-7 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-3 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) + Reducer 6 <- Map 1 (SIMPLE_EDGE) + Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl_n0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) + outputColumnNames: c1, c2, c3, c4 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c4) + keys: c1 (type: int), c2 (type: int), c3 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Select Operator + expressions: c1 (type: int), c2 (type: int), c3 (type: int) + outputColumnNames: c1, c2, c3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c3) + keys: c1 (type: int), c2 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Select Operator + expressions: c1 (type: int), c2 (type: int) + outputColumnNames: c1, c2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(c2) + keys: c1 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest3_n4 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) + outputColumnNames: d1, d2, d3, d4 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + outputColumnNames: d1, d2, d3 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n116 + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: d1, d2 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 896 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 896 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-4 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest3_n4 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3, d4 + Column Types: int, int, int, int + Table: default.dest3_n4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest2_n30 + + Stage: Stage-6 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2, d3 + Column Types: int, int, int + Table: default.dest2_n30 + + Stage: Stage-2 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n116 + + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: d1, d2 + Column Types: int, int + Table: default.dest1_n116 + diff --git ql/src/test/results/clientpositive/named_column_join.q.out ql/src/test/results/clientpositive/llap/named_column_join.q.out similarity index 78% rename from ql/src/test/results/clientpositive/named_column_join.q.out rename to ql/src/test/results/clientpositive/llap/named_column_join.q.out index 9c0250e5e5..23075f0df1 100644 --- ql/src/test/results/clientpositive/named_column_join.q.out +++ ql/src/test/results/clientpositive/llap/named_column_join.q.out @@ -30,64 +30,78 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: a is not null (type: boolean) - Statistics: Num rows: 8 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: a is not null (type: boolean) - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int), b (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) - TableScan - alias: t2 - filterExpr: a is not null (type: boolean) - Statistics: Num rows: 8 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: a is not null (type: boolean) - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int), b (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 9 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: a is not null (type: boolean) + Statistics: Num rows: 8 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: a is not null (type: boolean) + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: a (type: int), b (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: a is not null (type: boolean) + Statistics: Num rows: 8 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: a is not null (type: boolean) + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: a (type: int), b (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 6 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 9 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 9 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/nested_column_pruning.q.out ql/src/test/results/clientpositive/llap/nested_column_pruning.q.out new file mode 100644 index 0000000000..f064a5379b --- /dev/null +++ ql/src/test/results/clientpositive/llap/nested_column_pruning.q.out @@ -0,0 +1,2205 @@ +PREHOOK: query: DROP TABLE IF EXISTS dummy_n5 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS dummy_n5 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE dummy_n5 (i int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dummy_n5 +POSTHOOK: query: CREATE TABLE dummy_n5 (i int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dummy_n5 +PREHOOK: query: INSERT INTO TABLE dummy_n5 VALUES (42) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@dummy_n5 +POSTHOOK: query: INSERT INTO TABLE dummy_n5 VALUES (42) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@dummy_n5 +POSTHOOK: Lineage: dummy_n5.i SCRIPT [] +PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE nested_tbl_1_n1 ( + a int, + s1 struct, f6: int>, + s2 struct, f11: map>>, + s3 struct>>, + s4 map>, + s5 struct>>>, + s6 map>>>> +) STORED AS PARQUET +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nested_tbl_1_n1 +POSTHOOK: query: CREATE TABLE nested_tbl_1_n1 ( + a int, + s1 struct, f6: int>, + s2 struct, f11: map>>, + s3 struct>>, + s4 map>, + s5 struct>>>, + s6 map>>>> +) STORED AS PARQUET +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nested_tbl_1_n1 +PREHOOK: query: INSERT INTO TABLE nested_tbl_1_n1 SELECT + 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), + named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), + named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), + map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), + named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), + map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), + 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) +FROM dummy_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@dummy_n5 +PREHOOK: Output: default@nested_tbl_1_n1 +POSTHOOK: query: INSERT INTO TABLE nested_tbl_1_n1 SELECT + 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), + named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), + named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), + map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), + named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), + map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), + 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) +FROM dummy_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dummy_n5 +POSTHOOK: Output: default@nested_tbl_1_n1 +POSTHOOK: Lineage: nested_tbl_1_n1.a SIMPLE [] +POSTHOOK: Lineage: nested_tbl_1_n1.s1 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n1.s2 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n1.s3 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n1.s4 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n1.s5 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n1.s6 EXPRESSION [] +PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE nested_tbl_2_n1 LIKE nested_tbl_1_n1 +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nested_tbl_2_n1 +POSTHOOK: query: CREATE TABLE nested_tbl_2_n1 LIKE nested_tbl_1_n1 +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nested_tbl_2_n1 +PREHOOK: query: INSERT INTO TABLE nested_tbl_2_n1 SELECT + 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), + named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), + named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), + map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), + named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), + map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), + 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) +FROM dummy_n5 +PREHOOK: type: QUERY +PREHOOK: Input: default@dummy_n5 +PREHOOK: Output: default@nested_tbl_2_n1 +POSTHOOK: query: INSERT INTO TABLE nested_tbl_2_n1 SELECT + 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), + named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), + named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), + map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), + named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), + map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), + 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) +FROM dummy_n5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dummy_n5 +POSTHOOK: Output: default@nested_tbl_2_n1 +POSTHOOK: Lineage: nested_tbl_2_n1.a SIMPLE [] +POSTHOOK: Lineage: nested_tbl_2_n1.s1 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n1.s2 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n1.s3 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n1.s4 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n1.s5 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n1.s6 EXPRESSION [] +PREHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +1 +PREHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f1 (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +false +PREHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f1, s1.f2 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f1 (type: boolean), s1.f2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +false foo +PREHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f3 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +{"f4":4,"f5":5.0} 4 +PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f3.f5 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +5.0 +PREHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f3.f4, s2.f8.f9 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f4 (type: int), s2.f8.f9 (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +4 true +PREHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + filterExpr: (not s1.f1) (type: boolean) + Pruned Column Paths: s1.f2, s1.f1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (not s1.f1) (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f2 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +foo +PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + filterExpr: (s1.f3.f4 = 4) (type: boolean) + Pruned Column Paths: s1.f3.f5, s1.f3.f4 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f3.f4 = 4) (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +5.0 +PREHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + filterExpr: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) + Pruned Column Paths: s1.f2, s2.f8 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s2.f8 (type: struct,f11:map>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +{"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} +PREHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n1 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n1 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s2.f8.f10 + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s3 (type: struct>>) + outputColumnNames: s3 + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col3, _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int) + outputColumnNames: _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col3.f12 (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: s2.f8.f10 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col3, _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int) + outputColumnNames: _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col3.f12 (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n1 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n1 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +10 {"f13":"foo","f14":14} +10 {"f13":"bar","f14":28} +11 {"f13":"foo","f14":14} +11 {"f13":"bar","f14":28} +PREHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s2.f8.f10, s1.f3.f4 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (s2.f8.f10[1] pmod s1.f3.f4) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +3 +PREHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f3.f5, s1.f3.f4 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f5 (type: double), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: double) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +5.0 1 +PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f3 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: struct) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: struct) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: struct) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +{"f4":4,"f5":5.0} 1 +PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f3 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: struct) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: struct) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: struct) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct) + null sort order: z + sort order: + + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +{"f4":4,"f5":5.0} 1 +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +PREHOOK: Input: default@nested_tbl_2_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +POSTHOOK: Input: default@nested_tbl_2_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f3.f4 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f3.f4 (type: int) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f6 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f6 (type: int) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0.f3.f4 (type: int) + 1 _col0.f6 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +PREHOOK: Input: default@nested_tbl_2_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +POSTHOOK: Input: default@nested_tbl_2_n1 +#### A masked pattern was here #### +5.0 {"f9":false,"f10":[20,22],"f11":{"key3":true,"key4":false}} +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f3.f4 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f3.f4 (type: int) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (s1.f6 is not null and s2.f8.f9) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f6 is not null and s2.f8.f9) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f6 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f6 (type: int) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0.f3.f4 (type: int) + 1 _col0.f6 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +5.0 {"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), true (type: boolean) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: int), true (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) + Pruned Column Paths: s1.f6, s2.f8.f9 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f6 (type: int), s2.f8.f9 (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: int), _col1 (type: boolean) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: boolean) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: int), true (type: boolean) + 1 _col0 (type: int), _col1 (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +5.0 +Warning: Shuffle Join MERGEJOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 3 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 3 + Map Operator Tree: + TableScan + alias: t2 + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s2 (type: struct,f11:map>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + residual filter predicates: {(_col0.f1 <> _col1.f8.f9)} + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +5.0 +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: s1.f6 is not null (type: boolean) + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f6 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s2 (type: struct,f11:map>>), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col2 + residual filter predicates: {(_col0.f1 <> _col2.f8.f9)} + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +5.0 +PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE nested_tbl_3_n1 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS PARQUET +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nested_tbl_3_n1 +POSTHOOK: query: CREATE TABLE nested_tbl_3_n1 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS PARQUET +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nested_tbl_3_n1 +PREHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n1 PARTITION(f3) +SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 +FROM nested_tbl_1_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +PREHOOK: Output: default@nested_tbl_3_n1 +POSTHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n1 PARTITION(f3) +SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 +FROM nested_tbl_1_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +POSTHOOK: Output: default@nested_tbl_3_n1@f3=4 +POSTHOOK: Lineage: nested_tbl_3_n1 PARTITION(f3=4).f1 EXPRESSION [(nested_tbl_1_n1)nested_tbl_1_n1.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] +POSTHOOK: Lineage: nested_tbl_3_n1 PARTITION(f3=4).f2 EXPRESSION [(nested_tbl_1_n1)nested_tbl_1_n1.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] +PREHOOK: query: SELECT * FROM nested_tbl_3_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_3_n1 +PREHOOK: Input: default@nested_tbl_3_n1@f3=4 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM nested_tbl_3_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_3_n1 +POSTHOOK: Input: default@nested_tbl_3_n1@f3=4 +#### A masked pattern was here #### +false foo 4 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n1 +GROUP BY s3.f12[0].f14 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n1 +GROUP BY s3.f12[0].f14 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s3.f12, s1.f6 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s3.f12[0].f14 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n1 +GROUP BY s3.f12[0].f14 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n1 +GROUP BY s3.f12[0].f14 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +1 14 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n1 +GROUP BY s4['key1'].f15 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n1 +GROUP BY s4['key1'].f15 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s4['key1'].f15 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n1 +GROUP BY s4['key1'].f15 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n1 +GROUP BY s4['key1'].f15 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +1 1 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16[0].f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16[0].f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s5.f16, s1.f6 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s5.f16[0].f18.f19 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16[0].f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16[0].f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +1 14 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16.f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16.f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f6, s5.f16 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s5 (type: struct>>>) + outputColumnNames: s1, s5 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(s1.f6) + keys: s5.f16.f18.f19 (type: array) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: array) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: array) + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: array) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: array) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16.f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n1 +GROUP BY s5.f16.f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +1 [14,28] +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20[0].f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20[0].f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s6['key1'].f20[0].f21.f22 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20[0].f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20[0].f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +1 1 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20.f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20.f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n1 + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s6 (type: map>>>>) + outputColumnNames: s1, s6 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(s1.f6) + keys: s6['key1'].f20.f21.f22 (type: array) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: array) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: array) + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: array) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: array) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20.f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n1 +GROUP BY s6['key1'].f20.f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n1 +#### A masked pattern was here #### +1 [1] diff --git ql/src/test/results/clientpositive/llap/no_hooks.q.out ql/src/test/results/clientpositive/llap/no_hooks.q.out new file mode 100644 index 0000000000..b1ad498800 --- /dev/null +++ ql/src/test/results/clientpositive/llap/no_hooks.q.out @@ -0,0 +1,201 @@ +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +POSTHOOK: query: EXPLAIN +SELECT * FROM src src1 JOIN src src2 WHERE src1.key < 10 and src2.key < 10 SORT BY src1.key, src1.value, src2.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src2 + filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + sort order: ++++ + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +POSTHOOK: query: SELECT * FROM src src1 JOIN src src2 WHERE src1.key < 10 and src2.key < 10 SORT BY src1.key, src1.value, src2.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 9 val_9 +0 val_0 9 val_9 +0 val_0 9 val_9 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 2 val_2 +2 val_2 4 val_4 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 8 val_8 +2 val_2 9 val_9 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 2 val_2 +4 val_4 4 val_4 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 8 val_8 +4 val_4 9 val_9 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 9 val_9 +5 val_5 9 val_9 +5 val_5 9 val_9 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 2 val_2 +8 val_8 4 val_4 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 8 val_8 +8 val_8 9 val_9 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 2 val_2 +9 val_9 4 val_4 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 8 val_8 +9 val_9 9 val_9 diff --git ql/src/test/results/clientpositive/noalias_subq1.q.out ql/src/test/results/clientpositive/llap/noalias_subq1.q.out similarity index 52% rename from ql/src/test/results/clientpositive/noalias_subq1.q.out rename to ql/src/test/results/clientpositive/llap/noalias_subq1.q.out index 7cbb6ac993..ed5437fc82 100644 --- ql/src/test/results/clientpositive/noalias_subq1.q.out +++ ql/src/test/results/clientpositive/llap/noalias_subq1.q.out @@ -9,38 +9,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) < 100.0D) (type: boolean) + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: SELECT c1 FROM (select value as c1, key as c2 from src) x where c2 < 100 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/nonblock_op_deduplicate.q.out ql/src/test/results/clientpositive/llap/nonblock_op_deduplicate.q.out new file mode 100644 index 0000000000..f97fb64713 --- /dev/null +++ ql/src/test/results/clientpositive/llap/nonblock_op_deduplicate.q.out @@ -0,0 +1,337 @@ +PREHOOK: query: explain select nkey, nkey + 1 from (select key + 1 as nkey, value from src) a +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select nkey, nkey + 1 from (select key + 1 as nkey, value from src) a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Select Operator + expressions: (UDFToDouble(key) + 1.0D) (type: double), ((UDFToDouble(key) + 1.0D) + 1.0D) (type: double) + outputColumnNames: _col0, _col1 + ListSink + +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Reducer 4 (XPROD_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.96 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### + 25 + 25 + 25 + 25 + val_165 25 + val_193 25 + val_265 25 + val_27 25 + val_409 25 + val_484 25 +128 25 +146 val_146 25 +150 val_150 25 +213 val_213 25 +224 25 +238 val_238 25 +255 val_255 25 +273 val_273 25 +278 val_278 25 +311 val_311 25 +369 25 +401 val_401 25 +406 val_406 25 +66 val_66 25 +98 val_98 25 +Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: EXPLAIN +SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Reducer 3 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Reducer 3 + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: src1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.96 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Map 1' is a cross product +PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count +FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count + FROM (SELECT * + FROM (SELECT key, value + FROM src1) tmp1 ) tmp2 + JOIN (SELECT count(*) as count + FROM src1) tmp3 + ) tmp4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### + 25 + 25 + 25 + 25 + val_165 25 + val_193 25 + val_265 25 + val_27 25 + val_409 25 + val_484 25 +128 25 +146 val_146 25 +150 val_150 25 +213 val_213 25 +224 25 +238 val_238 25 +255 val_255 25 +273 val_273 25 +278 val_278 25 +311 val_311 25 +369 25 +401 val_401 25 +406 val_406 25 +66 val_66 25 +98 val_98 25 diff --git ql/src/test/results/clientpositive/llap/notable_alias1.q.out ql/src/test/results/clientpositive/llap/notable_alias1.q.out new file mode 100644 index 0000000000..8973d87b7a --- /dev/null +++ ql/src/test/results/clientpositive/llap/notable_alias1.q.out @@ -0,0 +1,211 @@ +PREHOOK: query: CREATE TABLE dest1_n4(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest1_n4 +POSTHOOK: query: CREATE TABLE dest1_n4(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest1_n4 +PREHOOK: query: EXPLAIN +FROM src +INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest1_n4 +POSTHOOK: query: EXPLAIN +FROM src +INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest1_n4 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) + outputColumnNames: dummy, key, value + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(dummy, 'hll'), compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9879518 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n4 + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: dummy, key, value + Column Types: string, int, double + Table: default.dest1_n4 + +PREHOOK: query: FROM src +INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest1_n4 +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest1_n4 +POSTHOOK: Lineage: dest1_n4.dummy SIMPLE [] +POSTHOOK: Lineage: dest1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_n4.value EXPRESSION [(src)src.null, ] +PREHOOK: query: SELECT dest1_n4.* FROM dest1_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1_n4 +#### A masked pattern was here #### +POSTHOOK: query: SELECT dest1_n4.* FROM dest1_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1_n4 +#### A masked pattern was here #### +1234 0 3.0 +1234 10 1.0 +1234 11 1.0 +1234 12 2.0 +1234 15 2.0 +1234 17 1.0 +1234 18 2.0 +1234 19 1.0 +1234 2 1.0 +1234 20 1.0 +1234 24 2.0 +1234 26 2.0 +1234 27 1.0 +1234 28 1.0 +1234 30 1.0 +1234 33 1.0 +1234 34 1.0 +1234 35 3.0 +1234 37 2.0 +1234 4 1.0 +1234 41 1.0 +1234 42 2.0 +1234 43 1.0 +1234 44 1.0 +1234 47 1.0 +1234 5 3.0 +1234 51 2.0 +1234 53 1.0 +1234 54 1.0 +1234 57 1.0 +1234 58 2.0 +1234 64 1.0 +1234 65 1.0 +1234 66 1.0 +1234 67 2.0 +1234 69 1.0 +1234 70 3.0 +1234 72 2.0 +1234 74 1.0 +1234 76 2.0 +1234 77 1.0 +1234 78 1.0 +1234 8 1.0 +1234 80 1.0 +1234 82 1.0 +1234 83 2.0 +1234 84 2.0 +1234 85 1.0 +1234 86 1.0 +1234 87 1.0 +1234 9 1.0 +1234 90 3.0 +1234 92 1.0 +1234 95 2.0 +1234 96 1.0 +1234 97 2.0 +1234 98 2.0 diff --git ql/src/test/results/clientpositive/llap/notable_alias2.q.out ql/src/test/results/clientpositive/llap/notable_alias2.q.out new file mode 100644 index 0000000000..e1b0aa870e --- /dev/null +++ ql/src/test/results/clientpositive/llap/notable_alias2.q.out @@ -0,0 +1,211 @@ +PREHOOK: query: CREATE TABLE dest1_n50(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest1_n50 +POSTHOOK: query: CREATE TABLE dest1_n50(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest1_n50 +PREHOOK: query: EXPLAIN +FROM src +INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest1_n50 +POSTHOOK: query: EXPLAIN +FROM src +INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest1_n50 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n50 + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) + outputColumnNames: dummy, key, value + Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(dummy, 'hll'), compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9879518 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n50 + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: dummy, key, value + Column Types: string, int, double + Table: default.dest1_n50 + +PREHOOK: query: FROM src +INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest1_n50 +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest1_n50 +POSTHOOK: Lineage: dest1_n50.dummy SIMPLE [] +POSTHOOK: Lineage: dest1_n50.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_n50.value EXPRESSION [(src)src.null, ] +PREHOOK: query: SELECT dest1_n50.* FROM dest1_n50 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1_n50 +#### A masked pattern was here #### +POSTHOOK: query: SELECT dest1_n50.* FROM dest1_n50 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1_n50 +#### A masked pattern was here #### +1234 0 3.0 +1234 10 1.0 +1234 11 1.0 +1234 12 2.0 +1234 15 2.0 +1234 17 1.0 +1234 18 2.0 +1234 19 1.0 +1234 2 1.0 +1234 20 1.0 +1234 24 2.0 +1234 26 2.0 +1234 27 1.0 +1234 28 1.0 +1234 30 1.0 +1234 33 1.0 +1234 34 1.0 +1234 35 3.0 +1234 37 2.0 +1234 4 1.0 +1234 41 1.0 +1234 42 2.0 +1234 43 1.0 +1234 44 1.0 +1234 47 1.0 +1234 5 3.0 +1234 51 2.0 +1234 53 1.0 +1234 54 1.0 +1234 57 1.0 +1234 58 2.0 +1234 64 1.0 +1234 65 1.0 +1234 66 1.0 +1234 67 2.0 +1234 69 1.0 +1234 70 3.0 +1234 72 2.0 +1234 74 1.0 +1234 76 2.0 +1234 77 1.0 +1234 78 1.0 +1234 8 1.0 +1234 80 1.0 +1234 82 1.0 +1234 83 2.0 +1234 84 2.0 +1234 85 1.0 +1234 86 1.0 +1234 87 1.0 +1234 9 1.0 +1234 90 3.0 +1234 92 1.0 +1234 95 2.0 +1234 96 1.0 +1234 97 2.0 +1234 98 2.0 diff --git ql/src/test/results/clientpositive/null_cast.q.out ql/src/test/results/clientpositive/llap/null_cast.q.out similarity index 50% rename from ql/src/test/results/clientpositive/null_cast.q.out rename to ql/src/test/results/clientpositive/llap/null_cast.q.out index 280a5a1267..40005b298a 100644 --- ql/src/test/results/clientpositive/null_cast.q.out +++ ql/src/test/results/clientpositive/llap/null_cast.q.out @@ -15,34 +15,20 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Row Limit Per Split: 1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(null,0) (type: array), array(null,array()) (type: array>), array(null,map()) (type: array>), array(null,const struct(0)) (type: array>) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 108000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 108000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + Row Limit Per Split: 1 + Select Operator + expressions: array(null,0) (type: array), array(null,array()) (type: array>), array(null,map()) (type: array>), array(null,const struct(0)) (type: array>) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: SELECT ARRAY(NULL, 0), ARRAY(NULL, ARRAY()), diff --git ql/src/test/results/clientpositive/nullability_transitive_inference.q.out ql/src/test/results/clientpositive/llap/nullability_transitive_inference.q.out similarity index 62% rename from ql/src/test/results/clientpositive/nullability_transitive_inference.q.out rename to ql/src/test/results/clientpositive/llap/nullability_transitive_inference.q.out index fe3f33bf3e..8c9985e970 100644 --- ql/src/test/results/clientpositive/nullability_transitive_inference.q.out +++ ql/src/test/results/clientpositive/llap/nullability_transitive_inference.q.out @@ -114,59 +114,73 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: emps_n6 - filterExpr: (deptno >= 20) (type: boolean) - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (deptno >= 20) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: empid (type: int), deptno (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - TableScan - alias: depts_n5 - filterExpr: (deptno >= 20) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (deptno >= 20) (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: deptno (type: int) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: emps_n6 + filterExpr: (deptno >= 20) (type: boolean) + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (deptno >= 20) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: empid (type: int), deptno (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: may be used (ACID table) + Map 3 + Map Operator Tree: + TableScan + alias: depts_n5 + filterExpr: (deptno >= 20) (type: boolean) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (deptno >= 20) (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: deptno (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: may be used (ACID table) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/nullgroup.q.out ql/src/test/results/clientpositive/llap/nullgroup.q.out new file mode 100644 index 0000000000..9cf2a30aa5 --- /dev/null +++ ql/src/test/results/clientpositive/llap/nullgroup.q.out @@ -0,0 +1,309 @@ +PREHOOK: query: explain +select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: final + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 +PREHOOK: query: explain +select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 +PREHOOK: query: explain +select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count() + mode: partial1 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: final + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 +PREHOOK: query: explain +select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count() + mode: complete + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1) from src x where x.key > 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from src x where x.key > 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 diff --git ql/src/test/results/clientpositive/llap/nullgroup2.q.out ql/src/test/results/clientpositive/llap/nullgroup2.q.out new file mode 100644 index 0000000000..6f21c5821a --- /dev/null +++ ql/src/test/results/clientpositive/llap/nullgroup2.q.out @@ -0,0 +1,330 @@ +PREHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: partials + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: rand() (type: double) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: partial1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +PREHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count() + keys: KEY._col0 (type: string) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/nullgroup3.q.out ql/src/test/results/clientpositive/llap/nullgroup3.q.out similarity index 64% rename from ql/src/test/results/clientpositive/nullgroup3.q.out rename to ql/src/test/results/clientpositive/llap/nullgroup3.q.out index 57d87feb92..bacaa6c287 100644 --- ql/src/test/results/clientpositive/nullgroup3.q.out +++ ql/src/test/results/clientpositive/llap/nullgroup3.q.out @@ -44,38 +44,47 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tstparttbl_n0 - Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tstparttbl_n0 + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -142,38 +151,47 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tstparttbl2_n0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tstparttbl2_n0 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -248,38 +266,47 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tstparttbl_n0 - Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tstparttbl_n0 + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + Statistics: Num rows: 120 Data size: 59080 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -354,38 +381,47 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tstparttbl2_n0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tstparttbl2_n0 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/nullgroup4.q.out ql/src/test/results/clientpositive/llap/nullgroup4.q.out new file mode 100644 index 0000000000..5fd9e0ebdc --- /dev/null +++ ql/src/test/results/clientpositive/llap/nullgroup4.q.out @@ -0,0 +1,359 @@ +PREHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(DISTINCT value) + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 125 Data size: 13375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 125 Data size: 13375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0) + mode: partials + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 0 +PREHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: partial2 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1), count(_col0) + mode: partial2 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 0 +PREHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: value (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(), count(DISTINCT KEY._col0:0._col0) + mode: partial1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 0 +PREHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: value (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(), count(DISTINCT KEY._col0:0._col0) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 0 diff --git ql/src/test/results/clientpositive/llap/nullgroup4_multi_distinct.q.out ql/src/test/results/clientpositive/llap/nullgroup4_multi_distinct.q.out new file mode 100644 index 0000000000..ef63c5f885 --- /dev/null +++ ql/src/test/results/clientpositive/llap/nullgroup4_multi_distinct.q.out @@ -0,0 +1,154 @@ +PREHOOK: query: explain +select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), substr(value, 5) (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(DISTINCT _col0), count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 125 Data size: 25125 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Statistics: Num rows: 125 Data size: 25125 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 0 0 +PREHOOK: query: explain +select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), substr(value, 5) (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) + mode: complete + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 0 0 diff --git ql/src/test/results/clientpositive/nullgroup5.q.out ql/src/test/results/clientpositive/llap/nullgroup5.q.out similarity index 77% rename from ql/src/test/results/clientpositive/nullgroup5.q.out rename to ql/src/test/results/clientpositive/llap/nullgroup5.q.out index 77eeafcfb9..0c3d506767 100644 --- ql/src/test/results/clientpositive/nullgroup5.q.out +++ ql/src/test/results/clientpositive/llap/nullgroup5.q.out @@ -62,45 +62,56 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (ds = '2009-04-05') (type: boolean) - Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (ds = '2009-04-05') (type: boolean) - Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 121 Data size: 39544 Basic stats: PARTIAL Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 121 Data size: 39544 Basic stats: PARTIAL Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: y - filterExpr: (ds = '2009-04-09') (type: boolean) - Statistics: Num rows: 120 Data size: 39376 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 120 Data size: 39376 Basic stats: PARTIAL Column stats: NONE - Union - Statistics: Num rows: 121 Data size: 39544 Basic stats: PARTIAL Column stats: PARTIAL - File Output Operator - compressed: false - Statistics: Num rows: 121 Data size: 39544 Basic stats: PARTIAL Column stats: PARTIAL - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 3 <- Union 2 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (ds = '2009-04-05') (type: boolean) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ds = '2009-04-05') (type: boolean) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 121 Data size: 39544 Basic stats: PARTIAL Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: unknown + Map 3 + Map Operator Tree: + TableScan + alias: y + filterExpr: (ds = '2009-04-09') (type: boolean) + Statistics: Num rows: 120 Data size: 39376 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 120 Data size: 39376 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 121 Data size: 39544 Basic stats: PARTIAL Column stats: PARTIAL + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Union 2 + Vertex: Union 2 Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/num_op_type_conv.q.out ql/src/test/results/clientpositive/llap/num_op_type_conv.q.out similarity index 84% rename from ql/src/test/results/clientpositive/num_op_type_conv.q.out rename to ql/src/test/results/clientpositive/llap/num_op_type_conv.q.out index a0884140f0..27ebfae73f 100644 --- ql/src/test/results/clientpositive/num_op_type_conv.q.out +++ ql/src/test/results/clientpositive/llap/num_op_type_conv.q.out @@ -22,14 +22,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: null (type: int), null (type: double), null (type: void), 1L (type: bigint), 0L (type: bigint), 0.0D (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 500 Data size: 12016 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT null + 7, 1.0 - null, null + null, diff --git ql/src/test/results/clientpositive/llap/offset_limit_global_optimizer.q.out ql/src/test/results/clientpositive/llap/offset_limit_global_optimizer.q.out new file mode 100644 index 0000000000..bf5c28670d --- /dev/null +++ ql/src/test/results/clientpositive/llap/offset_limit_global_optimizer.q.out @@ -0,0 +1,3828 @@ +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` +FROM `default`.`srcpart` +ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` +LIMIT 10 +OFFSET 400 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 410 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Offset of rows: 400 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +189 189 2008-04-08 11 +189 189 2008-04-08 12 +189 189 2008-04-09 11 +189 189 2008-04-09 12 +19 19 2008-04-08 11 +19 19 2008-04-08 12 +19 19 2008-04-09 11 +19 19 2008-04-09 12 +190 190 2008-04-08 11 +190 190 2008-04-08 12 +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` +FROM `default`.`srcpart` +ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` +LIMIT 10 +OFFSET 490 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 500 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Offset of rows: 490 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +201 201 2008-04-09 11 +201 201 2008-04-09 12 +202 202 2008-04-08 11 +202 202 2008-04-08 12 +202 202 2008-04-09 11 +202 202 2008-04-09 12 +203 203 2008-04-08 11 +203 203 2008-04-08 11 +203 203 2008-04-08 12 +203 203 2008-04-08 12 +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` +FROM `default`.`srcpart` +ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` +LIMIT 20 +OFFSET 490 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 510 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 20 + Offset of rows: 490 + Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +201 201 2008-04-09 11 +201 201 2008-04-09 12 +202 202 2008-04-08 11 +202 202 2008-04-08 12 +202 202 2008-04-09 11 +202 202 2008-04-09 12 +203 203 2008-04-08 11 +203 203 2008-04-08 11 +203 203 2008-04-08 12 +203 203 2008-04-08 12 +203 203 2008-04-09 11 +203 203 2008-04-09 11 +203 203 2008-04-09 12 +203 203 2008-04-09 12 +205 205 2008-04-08 11 +205 205 2008-04-08 11 +205 205 2008-04-08 12 +205 205 2008-04-08 12 +205 205 2008-04-09 11 +205 205 2008-04-09 11 +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` +FROM `default`.`srcpart` +ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` +LIMIT 600 +OFFSET 490 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 1090 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 600 + Offset of rows: 490 + Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 600 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +201 201 2008-04-09 11 +201 201 2008-04-09 12 +202 202 2008-04-08 11 +202 202 2008-04-08 12 +202 202 2008-04-09 11 +202 202 2008-04-09 12 +203 203 2008-04-08 11 +203 203 2008-04-08 11 +203 203 2008-04-08 12 +203 203 2008-04-08 12 +203 203 2008-04-09 11 +203 203 2008-04-09 11 +203 203 2008-04-09 12 +203 203 2008-04-09 12 +205 205 2008-04-08 11 +205 205 2008-04-08 11 +205 205 2008-04-08 12 +205 205 2008-04-08 12 +205 205 2008-04-09 11 +205 205 2008-04-09 11 +205 205 2008-04-09 12 +205 205 2008-04-09 12 +207 207 2008-04-08 11 +207 207 2008-04-08 11 +207 207 2008-04-08 12 +207 207 2008-04-08 12 +207 207 2008-04-09 11 +207 207 2008-04-09 11 +207 207 2008-04-09 12 +207 207 2008-04-09 12 +208 208 2008-04-08 11 +208 208 2008-04-08 11 +208 208 2008-04-08 11 +208 208 2008-04-08 12 +208 208 2008-04-08 12 +208 208 2008-04-08 12 +208 208 2008-04-09 11 +208 208 2008-04-09 11 +208 208 2008-04-09 11 +208 208 2008-04-09 12 +208 208 2008-04-09 12 +208 208 2008-04-09 12 +209 209 2008-04-08 11 +209 209 2008-04-08 11 +209 209 2008-04-08 12 +209 209 2008-04-08 12 +209 209 2008-04-09 11 +209 209 2008-04-09 11 +209 209 2008-04-09 12 +209 209 2008-04-09 12 +213 213 2008-04-08 11 +213 213 2008-04-08 11 +213 213 2008-04-08 12 +213 213 2008-04-08 12 +213 213 2008-04-09 11 +213 213 2008-04-09 11 +213 213 2008-04-09 12 +213 213 2008-04-09 12 +214 214 2008-04-08 11 +214 214 2008-04-08 12 +214 214 2008-04-09 11 +214 214 2008-04-09 12 +216 216 2008-04-08 11 +216 216 2008-04-08 11 +216 216 2008-04-08 12 +216 216 2008-04-08 12 +216 216 2008-04-09 11 +216 216 2008-04-09 11 +216 216 2008-04-09 12 +216 216 2008-04-09 12 +217 217 2008-04-08 11 +217 217 2008-04-08 11 +217 217 2008-04-08 12 +217 217 2008-04-08 12 +217 217 2008-04-09 11 +217 217 2008-04-09 11 +217 217 2008-04-09 12 +217 217 2008-04-09 12 +218 218 2008-04-08 11 +218 218 2008-04-08 12 +218 218 2008-04-09 11 +218 218 2008-04-09 12 +219 219 2008-04-08 11 +219 219 2008-04-08 11 +219 219 2008-04-08 12 +219 219 2008-04-08 12 +219 219 2008-04-09 11 +219 219 2008-04-09 11 +219 219 2008-04-09 12 +219 219 2008-04-09 12 +221 221 2008-04-08 11 +221 221 2008-04-08 11 +221 221 2008-04-08 12 +221 221 2008-04-08 12 +221 221 2008-04-09 11 +221 221 2008-04-09 11 +221 221 2008-04-09 12 +221 221 2008-04-09 12 +222 222 2008-04-08 11 +222 222 2008-04-08 12 +222 222 2008-04-09 11 +222 222 2008-04-09 12 +223 223 2008-04-08 11 +223 223 2008-04-08 11 +223 223 2008-04-08 12 +223 223 2008-04-08 12 +223 223 2008-04-09 11 +223 223 2008-04-09 11 +223 223 2008-04-09 12 +223 223 2008-04-09 12 +224 224 2008-04-08 11 +224 224 2008-04-08 11 +224 224 2008-04-08 12 +224 224 2008-04-08 12 +224 224 2008-04-09 11 +224 224 2008-04-09 11 +224 224 2008-04-09 12 +224 224 2008-04-09 12 +226 226 2008-04-08 11 +226 226 2008-04-08 12 +226 226 2008-04-09 11 +226 226 2008-04-09 12 +228 228 2008-04-08 11 +228 228 2008-04-08 12 +228 228 2008-04-09 11 +228 228 2008-04-09 12 +229 229 2008-04-08 11 +229 229 2008-04-08 11 +229 229 2008-04-08 12 +229 229 2008-04-08 12 +229 229 2008-04-09 11 +229 229 2008-04-09 11 +229 229 2008-04-09 12 +229 229 2008-04-09 12 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +233 233 2008-04-08 11 +233 233 2008-04-08 11 +233 233 2008-04-08 12 +233 233 2008-04-08 12 +233 233 2008-04-09 11 +233 233 2008-04-09 11 +233 233 2008-04-09 12 +233 233 2008-04-09 12 +235 235 2008-04-08 11 +235 235 2008-04-08 12 +235 235 2008-04-09 11 +235 235 2008-04-09 12 +237 237 2008-04-08 11 +237 237 2008-04-08 11 +237 237 2008-04-08 12 +237 237 2008-04-08 12 +237 237 2008-04-09 11 +237 237 2008-04-09 11 +237 237 2008-04-09 12 +237 237 2008-04-09 12 +238 238 2008-04-08 11 +238 238 2008-04-08 11 +238 238 2008-04-08 12 +238 238 2008-04-08 12 +238 238 2008-04-09 11 +238 238 2008-04-09 11 +238 238 2008-04-09 12 +238 238 2008-04-09 12 +239 239 2008-04-08 11 +239 239 2008-04-08 11 +239 239 2008-04-08 12 +239 239 2008-04-08 12 +239 239 2008-04-09 11 +239 239 2008-04-09 11 +239 239 2008-04-09 12 +239 239 2008-04-09 12 +24 24 2008-04-08 11 +24 24 2008-04-08 11 +24 24 2008-04-08 12 +24 24 2008-04-08 12 +24 24 2008-04-09 11 +24 24 2008-04-09 11 +24 24 2008-04-09 12 +24 24 2008-04-09 12 +241 241 2008-04-08 11 +241 241 2008-04-08 12 +241 241 2008-04-09 11 +241 241 2008-04-09 12 +242 242 2008-04-08 11 +242 242 2008-04-08 11 +242 242 2008-04-08 12 +242 242 2008-04-08 12 +242 242 2008-04-09 11 +242 242 2008-04-09 11 +242 242 2008-04-09 12 +242 242 2008-04-09 12 +244 244 2008-04-08 11 +244 244 2008-04-08 12 +244 244 2008-04-09 11 +244 244 2008-04-09 12 +247 247 2008-04-08 11 +247 247 2008-04-08 12 +247 247 2008-04-09 11 +247 247 2008-04-09 12 +248 248 2008-04-08 11 +248 248 2008-04-08 12 +248 248 2008-04-09 11 +248 248 2008-04-09 12 +249 249 2008-04-08 11 +249 249 2008-04-08 12 +249 249 2008-04-09 11 +249 249 2008-04-09 12 +252 252 2008-04-08 11 +252 252 2008-04-08 12 +252 252 2008-04-09 11 +252 252 2008-04-09 12 +255 255 2008-04-08 11 +255 255 2008-04-08 11 +255 255 2008-04-08 12 +255 255 2008-04-08 12 +255 255 2008-04-09 11 +255 255 2008-04-09 11 +255 255 2008-04-09 12 +255 255 2008-04-09 12 +256 256 2008-04-08 11 +256 256 2008-04-08 11 +256 256 2008-04-08 12 +256 256 2008-04-08 12 +256 256 2008-04-09 11 +256 256 2008-04-09 11 +256 256 2008-04-09 12 +256 256 2008-04-09 12 +257 257 2008-04-08 11 +257 257 2008-04-08 12 +257 257 2008-04-09 11 +257 257 2008-04-09 12 +258 258 2008-04-08 11 +258 258 2008-04-08 12 +258 258 2008-04-09 11 +258 258 2008-04-09 12 +26 26 2008-04-08 11 +26 26 2008-04-08 11 +26 26 2008-04-08 12 +26 26 2008-04-08 12 +26 26 2008-04-09 11 +26 26 2008-04-09 11 +26 26 2008-04-09 12 +26 26 2008-04-09 12 +260 260 2008-04-08 11 +260 260 2008-04-08 12 +260 260 2008-04-09 11 +260 260 2008-04-09 12 +262 262 2008-04-08 11 +262 262 2008-04-08 12 +262 262 2008-04-09 11 +262 262 2008-04-09 12 +263 263 2008-04-08 11 +263 263 2008-04-08 12 +263 263 2008-04-09 11 +263 263 2008-04-09 12 +265 265 2008-04-08 11 +265 265 2008-04-08 11 +265 265 2008-04-08 12 +265 265 2008-04-08 12 +265 265 2008-04-09 11 +265 265 2008-04-09 11 +265 265 2008-04-09 12 +265 265 2008-04-09 12 +266 266 2008-04-08 11 +266 266 2008-04-08 12 +266 266 2008-04-09 11 +266 266 2008-04-09 12 +27 27 2008-04-08 11 +27 27 2008-04-08 12 +27 27 2008-04-09 11 +27 27 2008-04-09 12 +272 272 2008-04-08 11 +272 272 2008-04-08 11 +272 272 2008-04-08 12 +272 272 2008-04-08 12 +272 272 2008-04-09 11 +272 272 2008-04-09 11 +272 272 2008-04-09 12 +272 272 2008-04-09 12 +273 273 2008-04-08 11 +273 273 2008-04-08 11 +273 273 2008-04-08 11 +273 273 2008-04-08 12 +273 273 2008-04-08 12 +273 273 2008-04-08 12 +273 273 2008-04-09 11 +273 273 2008-04-09 11 +273 273 2008-04-09 11 +273 273 2008-04-09 12 +273 273 2008-04-09 12 +273 273 2008-04-09 12 +274 274 2008-04-08 11 +274 274 2008-04-08 12 +274 274 2008-04-09 11 +274 274 2008-04-09 12 +275 275 2008-04-08 11 +275 275 2008-04-08 12 +275 275 2008-04-09 11 +275 275 2008-04-09 12 +277 277 2008-04-08 11 +277 277 2008-04-08 11 +277 277 2008-04-08 11 +277 277 2008-04-08 11 +277 277 2008-04-08 12 +277 277 2008-04-08 12 +277 277 2008-04-08 12 +277 277 2008-04-08 12 +277 277 2008-04-09 11 +277 277 2008-04-09 11 +277 277 2008-04-09 11 +277 277 2008-04-09 11 +277 277 2008-04-09 12 +277 277 2008-04-09 12 +277 277 2008-04-09 12 +277 277 2008-04-09 12 +278 278 2008-04-08 11 +278 278 2008-04-08 11 +278 278 2008-04-08 12 +278 278 2008-04-08 12 +278 278 2008-04-09 11 +278 278 2008-04-09 11 +278 278 2008-04-09 12 +278 278 2008-04-09 12 +28 28 2008-04-08 11 +28 28 2008-04-08 12 +28 28 2008-04-09 11 +28 28 2008-04-09 12 +280 280 2008-04-08 11 +280 280 2008-04-08 11 +280 280 2008-04-08 12 +280 280 2008-04-08 12 +280 280 2008-04-09 11 +280 280 2008-04-09 11 +280 280 2008-04-09 12 +280 280 2008-04-09 12 +281 281 2008-04-08 11 +281 281 2008-04-08 11 +281 281 2008-04-08 12 +281 281 2008-04-08 12 +281 281 2008-04-09 11 +281 281 2008-04-09 11 +281 281 2008-04-09 12 +281 281 2008-04-09 12 +282 282 2008-04-08 11 +282 282 2008-04-08 11 +282 282 2008-04-08 12 +282 282 2008-04-08 12 +282 282 2008-04-09 11 +282 282 2008-04-09 11 +282 282 2008-04-09 12 +282 282 2008-04-09 12 +283 283 2008-04-08 11 +283 283 2008-04-08 12 +283 283 2008-04-09 11 +283 283 2008-04-09 12 +284 284 2008-04-08 11 +284 284 2008-04-08 12 +284 284 2008-04-09 11 +284 284 2008-04-09 12 +285 285 2008-04-08 11 +285 285 2008-04-08 12 +285 285 2008-04-09 11 +285 285 2008-04-09 12 +286 286 2008-04-08 11 +286 286 2008-04-08 12 +286 286 2008-04-09 11 +286 286 2008-04-09 12 +287 287 2008-04-08 11 +287 287 2008-04-08 12 +287 287 2008-04-09 11 +287 287 2008-04-09 12 +288 288 2008-04-08 11 +288 288 2008-04-08 11 +288 288 2008-04-08 12 +288 288 2008-04-08 12 +288 288 2008-04-09 11 +288 288 2008-04-09 11 +288 288 2008-04-09 12 +288 288 2008-04-09 12 +289 289 2008-04-08 11 +289 289 2008-04-08 12 +289 289 2008-04-09 11 +289 289 2008-04-09 12 +291 291 2008-04-08 11 +291 291 2008-04-08 12 +291 291 2008-04-09 11 +291 291 2008-04-09 12 +292 292 2008-04-08 11 +292 292 2008-04-08 12 +292 292 2008-04-09 11 +292 292 2008-04-09 12 +296 296 2008-04-08 11 +296 296 2008-04-08 12 +296 296 2008-04-09 11 +296 296 2008-04-09 12 +298 298 2008-04-08 11 +298 298 2008-04-08 11 +298 298 2008-04-08 11 +298 298 2008-04-08 12 +298 298 2008-04-08 12 +298 298 2008-04-08 12 +298 298 2008-04-09 11 +298 298 2008-04-09 11 +298 298 2008-04-09 11 +298 298 2008-04-09 12 +298 298 2008-04-09 12 +298 298 2008-04-09 12 +30 30 2008-04-08 11 +30 30 2008-04-08 12 +30 30 2008-04-09 11 +30 30 2008-04-09 12 +302 302 2008-04-08 11 +302 302 2008-04-08 12 +302 302 2008-04-09 11 +302 302 2008-04-09 12 +305 305 2008-04-08 11 +305 305 2008-04-08 12 +305 305 2008-04-09 11 +305 305 2008-04-09 12 +306 306 2008-04-08 11 +306 306 2008-04-08 12 +306 306 2008-04-09 11 +306 306 2008-04-09 12 +307 307 2008-04-08 11 +307 307 2008-04-08 11 +307 307 2008-04-08 12 +307 307 2008-04-08 12 +307 307 2008-04-09 11 +307 307 2008-04-09 11 +307 307 2008-04-09 12 +307 307 2008-04-09 12 +308 308 2008-04-08 11 +308 308 2008-04-08 12 +308 308 2008-04-09 11 +308 308 2008-04-09 12 +309 309 2008-04-08 11 +309 309 2008-04-08 11 +309 309 2008-04-08 12 +309 309 2008-04-08 12 +309 309 2008-04-09 11 +309 309 2008-04-09 11 +309 309 2008-04-09 12 +309 309 2008-04-09 12 +310 310 2008-04-08 11 +310 310 2008-04-08 12 +310 310 2008-04-09 11 +310 310 2008-04-09 12 +311 311 2008-04-08 11 +311 311 2008-04-08 11 +311 311 2008-04-08 11 +311 311 2008-04-08 12 +311 311 2008-04-08 12 +311 311 2008-04-08 12 +311 311 2008-04-09 11 +311 311 2008-04-09 11 +311 311 2008-04-09 11 +311 311 2008-04-09 12 +311 311 2008-04-09 12 +311 311 2008-04-09 12 +315 315 2008-04-08 11 +315 315 2008-04-08 12 +315 315 2008-04-09 11 +315 315 2008-04-09 12 +316 316 2008-04-08 11 +316 316 2008-04-08 11 +316 316 2008-04-08 11 +316 316 2008-04-08 12 +316 316 2008-04-08 12 +316 316 2008-04-08 12 +316 316 2008-04-09 11 +316 316 2008-04-09 11 +316 316 2008-04-09 11 +316 316 2008-04-09 12 +316 316 2008-04-09 12 +316 316 2008-04-09 12 +317 317 2008-04-08 11 +317 317 2008-04-08 11 +317 317 2008-04-08 12 +317 317 2008-04-08 12 +317 317 2008-04-09 11 +317 317 2008-04-09 11 +317 317 2008-04-09 12 +317 317 2008-04-09 12 +318 318 2008-04-08 11 +318 318 2008-04-08 11 +318 318 2008-04-08 11 +318 318 2008-04-08 12 +318 318 2008-04-08 12 +318 318 2008-04-08 12 +318 318 2008-04-09 11 +318 318 2008-04-09 11 +318 318 2008-04-09 11 +318 318 2008-04-09 12 +318 318 2008-04-09 12 +318 318 2008-04-09 12 +321 321 2008-04-08 11 +321 321 2008-04-08 11 +321 321 2008-04-08 12 +321 321 2008-04-08 12 +321 321 2008-04-09 11 +321 321 2008-04-09 11 +321 321 2008-04-09 12 +321 321 2008-04-09 12 +322 322 2008-04-08 11 +322 322 2008-04-08 11 +322 322 2008-04-08 12 +322 322 2008-04-08 12 +322 322 2008-04-09 11 +322 322 2008-04-09 11 +322 322 2008-04-09 12 +322 322 2008-04-09 12 +323 323 2008-04-08 11 +323 323 2008-04-08 12 +323 323 2008-04-09 11 +323 323 2008-04-09 12 +325 325 2008-04-08 11 +325 325 2008-04-08 11 +325 325 2008-04-08 12 +325 325 2008-04-08 12 +325 325 2008-04-09 11 +325 325 2008-04-09 11 +325 325 2008-04-09 12 +325 325 2008-04-09 12 +327 327 2008-04-08 11 +327 327 2008-04-08 11 +327 327 2008-04-08 11 +327 327 2008-04-08 12 +327 327 2008-04-08 12 +327 327 2008-04-08 12 +327 327 2008-04-09 11 +327 327 2008-04-09 11 +327 327 2008-04-09 11 +327 327 2008-04-09 12 +327 327 2008-04-09 12 +327 327 2008-04-09 12 +33 33 2008-04-08 11 +33 33 2008-04-08 12 +33 33 2008-04-09 11 +33 33 2008-04-09 12 +331 331 2008-04-08 11 +331 331 2008-04-08 11 +331 331 2008-04-08 12 +331 331 2008-04-08 12 +331 331 2008-04-09 11 +331 331 2008-04-09 11 +331 331 2008-04-09 12 +331 331 2008-04-09 12 +332 332 2008-04-08 11 +332 332 2008-04-08 12 +332 332 2008-04-09 11 +332 332 2008-04-09 12 +333 333 2008-04-08 11 +333 333 2008-04-08 11 +333 333 2008-04-08 12 +333 333 2008-04-08 12 +333 333 2008-04-09 11 +333 333 2008-04-09 11 +333 333 2008-04-09 12 +333 333 2008-04-09 12 +335 335 2008-04-08 11 +335 335 2008-04-08 12 +335 335 2008-04-09 11 +335 335 2008-04-09 12 +336 336 2008-04-08 11 +336 336 2008-04-08 12 +336 336 2008-04-09 11 +336 336 2008-04-09 12 +338 338 2008-04-08 11 +338 338 2008-04-08 12 +338 338 2008-04-09 11 +338 338 2008-04-09 12 +339 339 2008-04-08 11 +339 339 2008-04-08 12 +339 339 2008-04-09 11 +339 339 2008-04-09 12 +34 34 2008-04-08 11 +34 34 2008-04-08 12 +34 34 2008-04-09 11 +34 34 2008-04-09 12 +341 341 2008-04-08 11 +341 341 2008-04-08 12 +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 410 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Offset of rows: 400 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +189 189 2008-04-08 11 +189 189 2008-04-08 12 +189 189 2008-04-09 11 +189 189 2008-04-09 12 +19 19 2008-04-08 11 +19 19 2008-04-08 12 +19 19 2008-04-09 11 +19 19 2008-04-09 12 +190 190 2008-04-08 11 +190 190 2008-04-08 12 +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 500 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Offset of rows: 490 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +201 201 2008-04-09 11 +201 201 2008-04-09 12 +202 202 2008-04-08 11 +202 202 2008-04-08 12 +202 202 2008-04-09 11 +202 202 2008-04-09 12 +203 203 2008-04-08 11 +203 203 2008-04-08 11 +203 203 2008-04-08 12 +203 203 2008-04-08 12 +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 510 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 20 + Offset of rows: 490 + Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +201 201 2008-04-09 11 +201 201 2008-04-09 12 +202 202 2008-04-08 11 +202 202 2008-04-08 12 +202 202 2008-04-09 11 +202 202 2008-04-09 12 +203 203 2008-04-08 11 +203 203 2008-04-08 11 +203 203 2008-04-08 12 +203 203 2008-04-08 12 +203 203 2008-04-09 11 +203 203 2008-04-09 11 +203 203 2008-04-09 12 +203 203 2008-04-09 12 +205 205 2008-04-08 11 +205 205 2008-04-08 11 +205 205 2008-04-08 12 +205 205 2008-04-08 12 +205 205 2008-04-09 11 +205 205 2008-04-09 11 +PREHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 1090 + TopN Hash Memory Usage: 0.1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 600 + Offset of rows: 490 + Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 600 + Processor Tree: + ListSink + +PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +201 201 2008-04-09 11 +201 201 2008-04-09 12 +202 202 2008-04-08 11 +202 202 2008-04-08 12 +202 202 2008-04-09 11 +202 202 2008-04-09 12 +203 203 2008-04-08 11 +203 203 2008-04-08 11 +203 203 2008-04-08 12 +203 203 2008-04-08 12 +203 203 2008-04-09 11 +203 203 2008-04-09 11 +203 203 2008-04-09 12 +203 203 2008-04-09 12 +205 205 2008-04-08 11 +205 205 2008-04-08 11 +205 205 2008-04-08 12 +205 205 2008-04-08 12 +205 205 2008-04-09 11 +205 205 2008-04-09 11 +205 205 2008-04-09 12 +205 205 2008-04-09 12 +207 207 2008-04-08 11 +207 207 2008-04-08 11 +207 207 2008-04-08 12 +207 207 2008-04-08 12 +207 207 2008-04-09 11 +207 207 2008-04-09 11 +207 207 2008-04-09 12 +207 207 2008-04-09 12 +208 208 2008-04-08 11 +208 208 2008-04-08 11 +208 208 2008-04-08 11 +208 208 2008-04-08 12 +208 208 2008-04-08 12 +208 208 2008-04-08 12 +208 208 2008-04-09 11 +208 208 2008-04-09 11 +208 208 2008-04-09 11 +208 208 2008-04-09 12 +208 208 2008-04-09 12 +208 208 2008-04-09 12 +209 209 2008-04-08 11 +209 209 2008-04-08 11 +209 209 2008-04-08 12 +209 209 2008-04-08 12 +209 209 2008-04-09 11 +209 209 2008-04-09 11 +209 209 2008-04-09 12 +209 209 2008-04-09 12 +213 213 2008-04-08 11 +213 213 2008-04-08 11 +213 213 2008-04-08 12 +213 213 2008-04-08 12 +213 213 2008-04-09 11 +213 213 2008-04-09 11 +213 213 2008-04-09 12 +213 213 2008-04-09 12 +214 214 2008-04-08 11 +214 214 2008-04-08 12 +214 214 2008-04-09 11 +214 214 2008-04-09 12 +216 216 2008-04-08 11 +216 216 2008-04-08 11 +216 216 2008-04-08 12 +216 216 2008-04-08 12 +216 216 2008-04-09 11 +216 216 2008-04-09 11 +216 216 2008-04-09 12 +216 216 2008-04-09 12 +217 217 2008-04-08 11 +217 217 2008-04-08 11 +217 217 2008-04-08 12 +217 217 2008-04-08 12 +217 217 2008-04-09 11 +217 217 2008-04-09 11 +217 217 2008-04-09 12 +217 217 2008-04-09 12 +218 218 2008-04-08 11 +218 218 2008-04-08 12 +218 218 2008-04-09 11 +218 218 2008-04-09 12 +219 219 2008-04-08 11 +219 219 2008-04-08 11 +219 219 2008-04-08 12 +219 219 2008-04-08 12 +219 219 2008-04-09 11 +219 219 2008-04-09 11 +219 219 2008-04-09 12 +219 219 2008-04-09 12 +221 221 2008-04-08 11 +221 221 2008-04-08 11 +221 221 2008-04-08 12 +221 221 2008-04-08 12 +221 221 2008-04-09 11 +221 221 2008-04-09 11 +221 221 2008-04-09 12 +221 221 2008-04-09 12 +222 222 2008-04-08 11 +222 222 2008-04-08 12 +222 222 2008-04-09 11 +222 222 2008-04-09 12 +223 223 2008-04-08 11 +223 223 2008-04-08 11 +223 223 2008-04-08 12 +223 223 2008-04-08 12 +223 223 2008-04-09 11 +223 223 2008-04-09 11 +223 223 2008-04-09 12 +223 223 2008-04-09 12 +224 224 2008-04-08 11 +224 224 2008-04-08 11 +224 224 2008-04-08 12 +224 224 2008-04-08 12 +224 224 2008-04-09 11 +224 224 2008-04-09 11 +224 224 2008-04-09 12 +224 224 2008-04-09 12 +226 226 2008-04-08 11 +226 226 2008-04-08 12 +226 226 2008-04-09 11 +226 226 2008-04-09 12 +228 228 2008-04-08 11 +228 228 2008-04-08 12 +228 228 2008-04-09 11 +228 228 2008-04-09 12 +229 229 2008-04-08 11 +229 229 2008-04-08 11 +229 229 2008-04-08 12 +229 229 2008-04-08 12 +229 229 2008-04-09 11 +229 229 2008-04-09 11 +229 229 2008-04-09 12 +229 229 2008-04-09 12 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 11 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-08 12 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 11 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +230 230 2008-04-09 12 +233 233 2008-04-08 11 +233 233 2008-04-08 11 +233 233 2008-04-08 12 +233 233 2008-04-08 12 +233 233 2008-04-09 11 +233 233 2008-04-09 11 +233 233 2008-04-09 12 +233 233 2008-04-09 12 +235 235 2008-04-08 11 +235 235 2008-04-08 12 +235 235 2008-04-09 11 +235 235 2008-04-09 12 +237 237 2008-04-08 11 +237 237 2008-04-08 11 +237 237 2008-04-08 12 +237 237 2008-04-08 12 +237 237 2008-04-09 11 +237 237 2008-04-09 11 +237 237 2008-04-09 12 +237 237 2008-04-09 12 +238 238 2008-04-08 11 +238 238 2008-04-08 11 +238 238 2008-04-08 12 +238 238 2008-04-08 12 +238 238 2008-04-09 11 +238 238 2008-04-09 11 +238 238 2008-04-09 12 +238 238 2008-04-09 12 +239 239 2008-04-08 11 +239 239 2008-04-08 11 +239 239 2008-04-08 12 +239 239 2008-04-08 12 +239 239 2008-04-09 11 +239 239 2008-04-09 11 +239 239 2008-04-09 12 +239 239 2008-04-09 12 +24 24 2008-04-08 11 +24 24 2008-04-08 11 +24 24 2008-04-08 12 +24 24 2008-04-08 12 +24 24 2008-04-09 11 +24 24 2008-04-09 11 +24 24 2008-04-09 12 +24 24 2008-04-09 12 +241 241 2008-04-08 11 +241 241 2008-04-08 12 +241 241 2008-04-09 11 +241 241 2008-04-09 12 +242 242 2008-04-08 11 +242 242 2008-04-08 11 +242 242 2008-04-08 12 +242 242 2008-04-08 12 +242 242 2008-04-09 11 +242 242 2008-04-09 11 +242 242 2008-04-09 12 +242 242 2008-04-09 12 +244 244 2008-04-08 11 +244 244 2008-04-08 12 +244 244 2008-04-09 11 +244 244 2008-04-09 12 +247 247 2008-04-08 11 +247 247 2008-04-08 12 +247 247 2008-04-09 11 +247 247 2008-04-09 12 +248 248 2008-04-08 11 +248 248 2008-04-08 12 +248 248 2008-04-09 11 +248 248 2008-04-09 12 +249 249 2008-04-08 11 +249 249 2008-04-08 12 +249 249 2008-04-09 11 +249 249 2008-04-09 12 +252 252 2008-04-08 11 +252 252 2008-04-08 12 +252 252 2008-04-09 11 +252 252 2008-04-09 12 +255 255 2008-04-08 11 +255 255 2008-04-08 11 +255 255 2008-04-08 12 +255 255 2008-04-08 12 +255 255 2008-04-09 11 +255 255 2008-04-09 11 +255 255 2008-04-09 12 +255 255 2008-04-09 12 +256 256 2008-04-08 11 +256 256 2008-04-08 11 +256 256 2008-04-08 12 +256 256 2008-04-08 12 +256 256 2008-04-09 11 +256 256 2008-04-09 11 +256 256 2008-04-09 12 +256 256 2008-04-09 12 +257 257 2008-04-08 11 +257 257 2008-04-08 12 +257 257 2008-04-09 11 +257 257 2008-04-09 12 +258 258 2008-04-08 11 +258 258 2008-04-08 12 +258 258 2008-04-09 11 +258 258 2008-04-09 12 +26 26 2008-04-08 11 +26 26 2008-04-08 11 +26 26 2008-04-08 12 +26 26 2008-04-08 12 +26 26 2008-04-09 11 +26 26 2008-04-09 11 +26 26 2008-04-09 12 +26 26 2008-04-09 12 +260 260 2008-04-08 11 +260 260 2008-04-08 12 +260 260 2008-04-09 11 +260 260 2008-04-09 12 +262 262 2008-04-08 11 +262 262 2008-04-08 12 +262 262 2008-04-09 11 +262 262 2008-04-09 12 +263 263 2008-04-08 11 +263 263 2008-04-08 12 +263 263 2008-04-09 11 +263 263 2008-04-09 12 +265 265 2008-04-08 11 +265 265 2008-04-08 11 +265 265 2008-04-08 12 +265 265 2008-04-08 12 +265 265 2008-04-09 11 +265 265 2008-04-09 11 +265 265 2008-04-09 12 +265 265 2008-04-09 12 +266 266 2008-04-08 11 +266 266 2008-04-08 12 +266 266 2008-04-09 11 +266 266 2008-04-09 12 +27 27 2008-04-08 11 +27 27 2008-04-08 12 +27 27 2008-04-09 11 +27 27 2008-04-09 12 +272 272 2008-04-08 11 +272 272 2008-04-08 11 +272 272 2008-04-08 12 +272 272 2008-04-08 12 +272 272 2008-04-09 11 +272 272 2008-04-09 11 +272 272 2008-04-09 12 +272 272 2008-04-09 12 +273 273 2008-04-08 11 +273 273 2008-04-08 11 +273 273 2008-04-08 11 +273 273 2008-04-08 12 +273 273 2008-04-08 12 +273 273 2008-04-08 12 +273 273 2008-04-09 11 +273 273 2008-04-09 11 +273 273 2008-04-09 11 +273 273 2008-04-09 12 +273 273 2008-04-09 12 +273 273 2008-04-09 12 +274 274 2008-04-08 11 +274 274 2008-04-08 12 +274 274 2008-04-09 11 +274 274 2008-04-09 12 +275 275 2008-04-08 11 +275 275 2008-04-08 12 +275 275 2008-04-09 11 +275 275 2008-04-09 12 +277 277 2008-04-08 11 +277 277 2008-04-08 11 +277 277 2008-04-08 11 +277 277 2008-04-08 11 +277 277 2008-04-08 12 +277 277 2008-04-08 12 +277 277 2008-04-08 12 +277 277 2008-04-08 12 +277 277 2008-04-09 11 +277 277 2008-04-09 11 +277 277 2008-04-09 11 +277 277 2008-04-09 11 +277 277 2008-04-09 12 +277 277 2008-04-09 12 +277 277 2008-04-09 12 +277 277 2008-04-09 12 +278 278 2008-04-08 11 +278 278 2008-04-08 11 +278 278 2008-04-08 12 +278 278 2008-04-08 12 +278 278 2008-04-09 11 +278 278 2008-04-09 11 +278 278 2008-04-09 12 +278 278 2008-04-09 12 +28 28 2008-04-08 11 +28 28 2008-04-08 12 +28 28 2008-04-09 11 +28 28 2008-04-09 12 +280 280 2008-04-08 11 +280 280 2008-04-08 11 +280 280 2008-04-08 12 +280 280 2008-04-08 12 +280 280 2008-04-09 11 +280 280 2008-04-09 11 +280 280 2008-04-09 12 +280 280 2008-04-09 12 +281 281 2008-04-08 11 +281 281 2008-04-08 11 +281 281 2008-04-08 12 +281 281 2008-04-08 12 +281 281 2008-04-09 11 +281 281 2008-04-09 11 +281 281 2008-04-09 12 +281 281 2008-04-09 12 +282 282 2008-04-08 11 +282 282 2008-04-08 11 +282 282 2008-04-08 12 +282 282 2008-04-08 12 +282 282 2008-04-09 11 +282 282 2008-04-09 11 +282 282 2008-04-09 12 +282 282 2008-04-09 12 +283 283 2008-04-08 11 +283 283 2008-04-08 12 +283 283 2008-04-09 11 +283 283 2008-04-09 12 +284 284 2008-04-08 11 +284 284 2008-04-08 12 +284 284 2008-04-09 11 +284 284 2008-04-09 12 +285 285 2008-04-08 11 +285 285 2008-04-08 12 +285 285 2008-04-09 11 +285 285 2008-04-09 12 +286 286 2008-04-08 11 +286 286 2008-04-08 12 +286 286 2008-04-09 11 +286 286 2008-04-09 12 +287 287 2008-04-08 11 +287 287 2008-04-08 12 +287 287 2008-04-09 11 +287 287 2008-04-09 12 +288 288 2008-04-08 11 +288 288 2008-04-08 11 +288 288 2008-04-08 12 +288 288 2008-04-08 12 +288 288 2008-04-09 11 +288 288 2008-04-09 11 +288 288 2008-04-09 12 +288 288 2008-04-09 12 +289 289 2008-04-08 11 +289 289 2008-04-08 12 +289 289 2008-04-09 11 +289 289 2008-04-09 12 +291 291 2008-04-08 11 +291 291 2008-04-08 12 +291 291 2008-04-09 11 +291 291 2008-04-09 12 +292 292 2008-04-08 11 +292 292 2008-04-08 12 +292 292 2008-04-09 11 +292 292 2008-04-09 12 +296 296 2008-04-08 11 +296 296 2008-04-08 12 +296 296 2008-04-09 11 +296 296 2008-04-09 12 +298 298 2008-04-08 11 +298 298 2008-04-08 11 +298 298 2008-04-08 11 +298 298 2008-04-08 12 +298 298 2008-04-08 12 +298 298 2008-04-08 12 +298 298 2008-04-09 11 +298 298 2008-04-09 11 +298 298 2008-04-09 11 +298 298 2008-04-09 12 +298 298 2008-04-09 12 +298 298 2008-04-09 12 +30 30 2008-04-08 11 +30 30 2008-04-08 12 +30 30 2008-04-09 11 +30 30 2008-04-09 12 +302 302 2008-04-08 11 +302 302 2008-04-08 12 +302 302 2008-04-09 11 +302 302 2008-04-09 12 +305 305 2008-04-08 11 +305 305 2008-04-08 12 +305 305 2008-04-09 11 +305 305 2008-04-09 12 +306 306 2008-04-08 11 +306 306 2008-04-08 12 +306 306 2008-04-09 11 +306 306 2008-04-09 12 +307 307 2008-04-08 11 +307 307 2008-04-08 11 +307 307 2008-04-08 12 +307 307 2008-04-08 12 +307 307 2008-04-09 11 +307 307 2008-04-09 11 +307 307 2008-04-09 12 +307 307 2008-04-09 12 +308 308 2008-04-08 11 +308 308 2008-04-08 12 +308 308 2008-04-09 11 +308 308 2008-04-09 12 +309 309 2008-04-08 11 +309 309 2008-04-08 11 +309 309 2008-04-08 12 +309 309 2008-04-08 12 +309 309 2008-04-09 11 +309 309 2008-04-09 11 +309 309 2008-04-09 12 +309 309 2008-04-09 12 +310 310 2008-04-08 11 +310 310 2008-04-08 12 +310 310 2008-04-09 11 +310 310 2008-04-09 12 +311 311 2008-04-08 11 +311 311 2008-04-08 11 +311 311 2008-04-08 11 +311 311 2008-04-08 12 +311 311 2008-04-08 12 +311 311 2008-04-08 12 +311 311 2008-04-09 11 +311 311 2008-04-09 11 +311 311 2008-04-09 11 +311 311 2008-04-09 12 +311 311 2008-04-09 12 +311 311 2008-04-09 12 +315 315 2008-04-08 11 +315 315 2008-04-08 12 +315 315 2008-04-09 11 +315 315 2008-04-09 12 +316 316 2008-04-08 11 +316 316 2008-04-08 11 +316 316 2008-04-08 11 +316 316 2008-04-08 12 +316 316 2008-04-08 12 +316 316 2008-04-08 12 +316 316 2008-04-09 11 +316 316 2008-04-09 11 +316 316 2008-04-09 11 +316 316 2008-04-09 12 +316 316 2008-04-09 12 +316 316 2008-04-09 12 +317 317 2008-04-08 11 +317 317 2008-04-08 11 +317 317 2008-04-08 12 +317 317 2008-04-08 12 +317 317 2008-04-09 11 +317 317 2008-04-09 11 +317 317 2008-04-09 12 +317 317 2008-04-09 12 +318 318 2008-04-08 11 +318 318 2008-04-08 11 +318 318 2008-04-08 11 +318 318 2008-04-08 12 +318 318 2008-04-08 12 +318 318 2008-04-08 12 +318 318 2008-04-09 11 +318 318 2008-04-09 11 +318 318 2008-04-09 11 +318 318 2008-04-09 12 +318 318 2008-04-09 12 +318 318 2008-04-09 12 +321 321 2008-04-08 11 +321 321 2008-04-08 11 +321 321 2008-04-08 12 +321 321 2008-04-08 12 +321 321 2008-04-09 11 +321 321 2008-04-09 11 +321 321 2008-04-09 12 +321 321 2008-04-09 12 +322 322 2008-04-08 11 +322 322 2008-04-08 11 +322 322 2008-04-08 12 +322 322 2008-04-08 12 +322 322 2008-04-09 11 +322 322 2008-04-09 11 +322 322 2008-04-09 12 +322 322 2008-04-09 12 +323 323 2008-04-08 11 +323 323 2008-04-08 12 +323 323 2008-04-09 11 +323 323 2008-04-09 12 +325 325 2008-04-08 11 +325 325 2008-04-08 11 +325 325 2008-04-08 12 +325 325 2008-04-08 12 +325 325 2008-04-09 11 +325 325 2008-04-09 11 +325 325 2008-04-09 12 +325 325 2008-04-09 12 +327 327 2008-04-08 11 +327 327 2008-04-08 11 +327 327 2008-04-08 11 +327 327 2008-04-08 12 +327 327 2008-04-08 12 +327 327 2008-04-08 12 +327 327 2008-04-09 11 +327 327 2008-04-09 11 +327 327 2008-04-09 11 +327 327 2008-04-09 12 +327 327 2008-04-09 12 +327 327 2008-04-09 12 +33 33 2008-04-08 11 +33 33 2008-04-08 12 +33 33 2008-04-09 11 +33 33 2008-04-09 12 +331 331 2008-04-08 11 +331 331 2008-04-08 11 +331 331 2008-04-08 12 +331 331 2008-04-08 12 +331 331 2008-04-09 11 +331 331 2008-04-09 11 +331 331 2008-04-09 12 +331 331 2008-04-09 12 +332 332 2008-04-08 11 +332 332 2008-04-08 12 +332 332 2008-04-09 11 +332 332 2008-04-09 12 +333 333 2008-04-08 11 +333 333 2008-04-08 11 +333 333 2008-04-08 12 +333 333 2008-04-08 12 +333 333 2008-04-09 11 +333 333 2008-04-09 11 +333 333 2008-04-09 12 +333 333 2008-04-09 12 +335 335 2008-04-08 11 +335 335 2008-04-08 12 +335 335 2008-04-09 11 +335 335 2008-04-09 12 +336 336 2008-04-08 11 +336 336 2008-04-08 12 +336 336 2008-04-09 11 +336 336 2008-04-09 12 +338 338 2008-04-08 11 +338 338 2008-04-08 12 +338 338 2008-04-09 11 +338 338 2008-04-09 12 +339 339 2008-04-08 11 +339 339 2008-04-08 12 +339 339 2008-04-09 11 +339 339 2008-04-09 12 +34 34 2008-04-08 11 +34 34 2008-04-08 12 +34 34 2008-04-09 11 +34 34 2008-04-09 12 +341 341 2008-04-08 11 +341 341 2008-04-08 12 diff --git ql/src/test/results/clientpositive/optimize_filter_literal.q.out ql/src/test/results/clientpositive/llap/optimize_filter_literal.q.out similarity index 97% rename from ql/src/test/results/clientpositive/optimize_filter_literal.q.out rename to ql/src/test/results/clientpositive/llap/optimize_filter_literal.q.out index 7542d76305..8257439881 100644 --- ql/src/test/results/clientpositive/optimize_filter_literal.q.out +++ ql/src/test/results/clientpositive/llap/optimize_filter_literal.q.out @@ -136,8 +136,8 @@ POSTHOOK: Input: default@tab_n14@ds=2008-04-08 POSTHOOK: Output: default@tab_n14 POSTHOOK: Output: default@tab_n14@ds=2008-04-08 #### A masked pattern was here #### -Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product PREHOOK: query: select * from (select * from tab_n14 where tab_n14.key = 0)a full outer join diff --git ql/src/test/results/clientpositive/llap/optional_outer.q.out ql/src/test/results/clientpositive/llap/optional_outer.q.out new file mode 100644 index 0000000000..4908f76f32 --- /dev/null +++ ql/src/test/results/clientpositive/llap/optional_outer.q.out @@ -0,0 +1,502 @@ +PREHOOK: query: EXPLAIN SELECT * FROM src a LEFT OUTER JOIN src b on (a.key=b.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src a LEFT OUTER JOIN src b on (a.key=b.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN SELECT * FROM src a LEFT JOIN src b on (a.key=b.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src a LEFT JOIN src b on (a.key=b.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN SELECT * FROM src a RIGHT OUTER JOIN src b on (a.key=b.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src a RIGHT OUTER JOIN src b on (a.key=b.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN SELECT * FROM src a RIGHT JOIN src b on (a.key=b.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src a RIGHT JOIN src b on (a.key=b.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN SELECT * FROM src a FULL OUTER JOIN src b on (a.key=b.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src a FULL OUTER JOIN src b on (a.key=b.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN SELECT * FROM src a FULL JOIN src b on (a.key=b.key) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src a FULL JOIN src b on (a.key=b.key) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/orc_avro_partition_uniontype.q.out ql/src/test/results/clientpositive/llap/orc_avro_partition_uniontype.q.out new file mode 100644 index 0000000000..c6003ecd13 --- /dev/null +++ ql/src/test/results/clientpositive/llap/orc_avro_partition_uniontype.q.out @@ -0,0 +1,535 @@ +PREHOOK: query: CREATE TABLE avro_orc_partitioned_uniontype (a uniontype) PARTITIONED BY (b int) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@avro_orc_partitioned_uniontype +POSTHOOK: query: CREATE TABLE avro_orc_partitioned_uniontype (a uniontype) PARTITIONED BY (b int) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@avro_orc_partitioned_uniontype +PREHOOK: query: INSERT INTO avro_orc_partitioned_uniontype PARTITION (b=1) SELECT create_union(1, true, value) FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@avro_orc_partitioned_uniontype@b=1 +POSTHOOK: query: INSERT INTO avro_orc_partitioned_uniontype PARTITION (b=1) SELECT create_union(1, true, value) FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@avro_orc_partitioned_uniontype@b=1 +POSTHOOK: Lineage: avro_orc_partitioned_uniontype PARTITION(b=1).a EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: ALTER TABLE avro_orc_partitioned_uniontype SET FILEFORMAT AVRO +PREHOOK: type: ALTERTABLE_FILEFORMAT +PREHOOK: Input: default@avro_orc_partitioned_uniontype +PREHOOK: Output: default@avro_orc_partitioned_uniontype +POSTHOOK: query: ALTER TABLE avro_orc_partitioned_uniontype SET FILEFORMAT AVRO +POSTHOOK: type: ALTERTABLE_FILEFORMAT +POSTHOOK: Input: default@avro_orc_partitioned_uniontype +POSTHOOK: Output: default@avro_orc_partitioned_uniontype +PREHOOK: query: SELECT * FROM avro_orc_partitioned_uniontype +PREHOOK: type: QUERY +PREHOOK: Input: default@avro_orc_partitioned_uniontype +PREHOOK: Input: default@avro_orc_partitioned_uniontype@b=1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM avro_orc_partitioned_uniontype +POSTHOOK: type: QUERY +POSTHOOK: Input: default@avro_orc_partitioned_uniontype +POSTHOOK: Input: default@avro_orc_partitioned_uniontype@b=1 +#### A masked pattern was here #### +{1:"val_0"} 1 +{1:"val_0"} 1 +{1:"val_0"} 1 +{1:"val_10"} 1 +{1:"val_100"} 1 +{1:"val_100"} 1 +{1:"val_103"} 1 +{1:"val_103"} 1 +{1:"val_104"} 1 +{1:"val_104"} 1 +{1:"val_105"} 1 +{1:"val_11"} 1 +{1:"val_111"} 1 +{1:"val_113"} 1 +{1:"val_113"} 1 +{1:"val_114"} 1 +{1:"val_116"} 1 +{1:"val_118"} 1 +{1:"val_118"} 1 +{1:"val_119"} 1 +{1:"val_119"} 1 +{1:"val_119"} 1 +{1:"val_12"} 1 +{1:"val_12"} 1 +{1:"val_120"} 1 +{1:"val_120"} 1 +{1:"val_125"} 1 +{1:"val_125"} 1 +{1:"val_126"} 1 +{1:"val_128"} 1 +{1:"val_128"} 1 +{1:"val_128"} 1 +{1:"val_129"} 1 +{1:"val_129"} 1 +{1:"val_131"} 1 +{1:"val_133"} 1 +{1:"val_134"} 1 +{1:"val_134"} 1 +{1:"val_136"} 1 +{1:"val_137"} 1 +{1:"val_137"} 1 +{1:"val_138"} 1 +{1:"val_138"} 1 +{1:"val_138"} 1 +{1:"val_138"} 1 +{1:"val_143"} 1 +{1:"val_145"} 1 +{1:"val_146"} 1 +{1:"val_146"} 1 +{1:"val_149"} 1 +{1:"val_149"} 1 +{1:"val_15"} 1 +{1:"val_15"} 1 +{1:"val_150"} 1 +{1:"val_152"} 1 +{1:"val_152"} 1 +{1:"val_153"} 1 +{1:"val_155"} 1 +{1:"val_156"} 1 +{1:"val_157"} 1 +{1:"val_158"} 1 +{1:"val_160"} 1 +{1:"val_162"} 1 +{1:"val_163"} 1 +{1:"val_164"} 1 +{1:"val_164"} 1 +{1:"val_165"} 1 +{1:"val_165"} 1 +{1:"val_166"} 1 +{1:"val_167"} 1 +{1:"val_167"} 1 +{1:"val_167"} 1 +{1:"val_168"} 1 +{1:"val_169"} 1 +{1:"val_169"} 1 +{1:"val_169"} 1 +{1:"val_169"} 1 +{1:"val_17"} 1 +{1:"val_170"} 1 +{1:"val_172"} 1 +{1:"val_172"} 1 +{1:"val_174"} 1 +{1:"val_174"} 1 +{1:"val_175"} 1 +{1:"val_175"} 1 +{1:"val_176"} 1 +{1:"val_176"} 1 +{1:"val_177"} 1 +{1:"val_178"} 1 +{1:"val_179"} 1 +{1:"val_179"} 1 +{1:"val_18"} 1 +{1:"val_18"} 1 +{1:"val_180"} 1 +{1:"val_181"} 1 +{1:"val_183"} 1 +{1:"val_186"} 1 +{1:"val_187"} 1 +{1:"val_187"} 1 +{1:"val_187"} 1 +{1:"val_189"} 1 +{1:"val_19"} 1 +{1:"val_190"} 1 +{1:"val_191"} 1 +{1:"val_191"} 1 +{1:"val_192"} 1 +{1:"val_193"} 1 +{1:"val_193"} 1 +{1:"val_193"} 1 +{1:"val_194"} 1 +{1:"val_195"} 1 +{1:"val_195"} 1 +{1:"val_196"} 1 +{1:"val_197"} 1 +{1:"val_197"} 1 +{1:"val_199"} 1 +{1:"val_199"} 1 +{1:"val_199"} 1 +{1:"val_2"} 1 +{1:"val_20"} 1 +{1:"val_200"} 1 +{1:"val_200"} 1 +{1:"val_201"} 1 +{1:"val_202"} 1 +{1:"val_203"} 1 +{1:"val_203"} 1 +{1:"val_205"} 1 +{1:"val_205"} 1 +{1:"val_207"} 1 +{1:"val_207"} 1 +{1:"val_208"} 1 +{1:"val_208"} 1 +{1:"val_208"} 1 +{1:"val_209"} 1 +{1:"val_209"} 1 +{1:"val_213"} 1 +{1:"val_213"} 1 +{1:"val_214"} 1 +{1:"val_216"} 1 +{1:"val_216"} 1 +{1:"val_217"} 1 +{1:"val_217"} 1 +{1:"val_218"} 1 +{1:"val_219"} 1 +{1:"val_219"} 1 +{1:"val_221"} 1 +{1:"val_221"} 1 +{1:"val_222"} 1 +{1:"val_223"} 1 +{1:"val_223"} 1 +{1:"val_224"} 1 +{1:"val_224"} 1 +{1:"val_226"} 1 +{1:"val_228"} 1 +{1:"val_229"} 1 +{1:"val_229"} 1 +{1:"val_230"} 1 +{1:"val_230"} 1 +{1:"val_230"} 1 +{1:"val_230"} 1 +{1:"val_230"} 1 +{1:"val_233"} 1 +{1:"val_233"} 1 +{1:"val_235"} 1 +{1:"val_237"} 1 +{1:"val_237"} 1 +{1:"val_238"} 1 +{1:"val_238"} 1 +{1:"val_239"} 1 +{1:"val_239"} 1 +{1:"val_24"} 1 +{1:"val_24"} 1 +{1:"val_241"} 1 +{1:"val_242"} 1 +{1:"val_242"} 1 +{1:"val_244"} 1 +{1:"val_247"} 1 +{1:"val_248"} 1 +{1:"val_249"} 1 +{1:"val_252"} 1 +{1:"val_255"} 1 +{1:"val_255"} 1 +{1:"val_256"} 1 +{1:"val_256"} 1 +{1:"val_257"} 1 +{1:"val_258"} 1 +{1:"val_26"} 1 +{1:"val_26"} 1 +{1:"val_260"} 1 +{1:"val_262"} 1 +{1:"val_263"} 1 +{1:"val_265"} 1 +{1:"val_265"} 1 +{1:"val_266"} 1 +{1:"val_27"} 1 +{1:"val_272"} 1 +{1:"val_272"} 1 +{1:"val_273"} 1 +{1:"val_273"} 1 +{1:"val_273"} 1 +{1:"val_274"} 1 +{1:"val_275"} 1 +{1:"val_277"} 1 +{1:"val_277"} 1 +{1:"val_277"} 1 +{1:"val_277"} 1 +{1:"val_278"} 1 +{1:"val_278"} 1 +{1:"val_28"} 1 +{1:"val_280"} 1 +{1:"val_280"} 1 +{1:"val_281"} 1 +{1:"val_281"} 1 +{1:"val_282"} 1 +{1:"val_282"} 1 +{1:"val_283"} 1 +{1:"val_284"} 1 +{1:"val_285"} 1 +{1:"val_286"} 1 +{1:"val_287"} 1 +{1:"val_288"} 1 +{1:"val_288"} 1 +{1:"val_289"} 1 +{1:"val_291"} 1 +{1:"val_292"} 1 +{1:"val_296"} 1 +{1:"val_298"} 1 +{1:"val_298"} 1 +{1:"val_298"} 1 +{1:"val_30"} 1 +{1:"val_302"} 1 +{1:"val_305"} 1 +{1:"val_306"} 1 +{1:"val_307"} 1 +{1:"val_307"} 1 +{1:"val_308"} 1 +{1:"val_309"} 1 +{1:"val_309"} 1 +{1:"val_310"} 1 +{1:"val_311"} 1 +{1:"val_311"} 1 +{1:"val_311"} 1 +{1:"val_315"} 1 +{1:"val_316"} 1 +{1:"val_316"} 1 +{1:"val_316"} 1 +{1:"val_317"} 1 +{1:"val_317"} 1 +{1:"val_318"} 1 +{1:"val_318"} 1 +{1:"val_318"} 1 +{1:"val_321"} 1 +{1:"val_321"} 1 +{1:"val_322"} 1 +{1:"val_322"} 1 +{1:"val_323"} 1 +{1:"val_325"} 1 +{1:"val_325"} 1 +{1:"val_327"} 1 +{1:"val_327"} 1 +{1:"val_327"} 1 +{1:"val_33"} 1 +{1:"val_331"} 1 +{1:"val_331"} 1 +{1:"val_332"} 1 +{1:"val_333"} 1 +{1:"val_333"} 1 +{1:"val_335"} 1 +{1:"val_336"} 1 +{1:"val_338"} 1 +{1:"val_339"} 1 +{1:"val_34"} 1 +{1:"val_341"} 1 +{1:"val_342"} 1 +{1:"val_342"} 1 +{1:"val_344"} 1 +{1:"val_344"} 1 +{1:"val_345"} 1 +{1:"val_348"} 1 +{1:"val_348"} 1 +{1:"val_348"} 1 +{1:"val_348"} 1 +{1:"val_348"} 1 +{1:"val_35"} 1 +{1:"val_35"} 1 +{1:"val_35"} 1 +{1:"val_351"} 1 +{1:"val_353"} 1 +{1:"val_353"} 1 +{1:"val_356"} 1 +{1:"val_360"} 1 +{1:"val_362"} 1 +{1:"val_364"} 1 +{1:"val_365"} 1 +{1:"val_366"} 1 +{1:"val_367"} 1 +{1:"val_367"} 1 +{1:"val_368"} 1 +{1:"val_369"} 1 +{1:"val_369"} 1 +{1:"val_369"} 1 +{1:"val_37"} 1 +{1:"val_37"} 1 +{1:"val_373"} 1 +{1:"val_374"} 1 +{1:"val_375"} 1 +{1:"val_377"} 1 +{1:"val_378"} 1 +{1:"val_379"} 1 +{1:"val_382"} 1 +{1:"val_382"} 1 +{1:"val_384"} 1 +{1:"val_384"} 1 +{1:"val_384"} 1 +{1:"val_386"} 1 +{1:"val_389"} 1 +{1:"val_392"} 1 +{1:"val_393"} 1 +{1:"val_394"} 1 +{1:"val_395"} 1 +{1:"val_395"} 1 +{1:"val_396"} 1 +{1:"val_396"} 1 +{1:"val_396"} 1 +{1:"val_397"} 1 +{1:"val_397"} 1 +{1:"val_399"} 1 +{1:"val_399"} 1 +{1:"val_4"} 1 +{1:"val_400"} 1 +{1:"val_401"} 1 +{1:"val_401"} 1 +{1:"val_401"} 1 +{1:"val_401"} 1 +{1:"val_401"} 1 +{1:"val_402"} 1 +{1:"val_403"} 1 +{1:"val_403"} 1 +{1:"val_403"} 1 +{1:"val_404"} 1 +{1:"val_404"} 1 +{1:"val_406"} 1 +{1:"val_406"} 1 +{1:"val_406"} 1 +{1:"val_406"} 1 +{1:"val_407"} 1 +{1:"val_409"} 1 +{1:"val_409"} 1 +{1:"val_409"} 1 +{1:"val_41"} 1 +{1:"val_411"} 1 +{1:"val_413"} 1 +{1:"val_413"} 1 +{1:"val_414"} 1 +{1:"val_414"} 1 +{1:"val_417"} 1 +{1:"val_417"} 1 +{1:"val_417"} 1 +{1:"val_418"} 1 +{1:"val_419"} 1 +{1:"val_42"} 1 +{1:"val_42"} 1 +{1:"val_421"} 1 +{1:"val_424"} 1 +{1:"val_424"} 1 +{1:"val_427"} 1 +{1:"val_429"} 1 +{1:"val_429"} 1 +{1:"val_43"} 1 +{1:"val_430"} 1 +{1:"val_430"} 1 +{1:"val_430"} 1 +{1:"val_431"} 1 +{1:"val_431"} 1 +{1:"val_431"} 1 +{1:"val_432"} 1 +{1:"val_435"} 1 +{1:"val_436"} 1 +{1:"val_437"} 1 +{1:"val_438"} 1 +{1:"val_438"} 1 +{1:"val_438"} 1 +{1:"val_439"} 1 +{1:"val_439"} 1 +{1:"val_44"} 1 +{1:"val_443"} 1 +{1:"val_444"} 1 +{1:"val_446"} 1 +{1:"val_448"} 1 +{1:"val_449"} 1 +{1:"val_452"} 1 +{1:"val_453"} 1 +{1:"val_454"} 1 +{1:"val_454"} 1 +{1:"val_454"} 1 +{1:"val_455"} 1 +{1:"val_457"} 1 +{1:"val_458"} 1 +{1:"val_458"} 1 +{1:"val_459"} 1 +{1:"val_459"} 1 +{1:"val_460"} 1 +{1:"val_462"} 1 +{1:"val_462"} 1 +{1:"val_463"} 1 +{1:"val_463"} 1 +{1:"val_466"} 1 +{1:"val_466"} 1 +{1:"val_466"} 1 +{1:"val_467"} 1 +{1:"val_468"} 1 +{1:"val_468"} 1 +{1:"val_468"} 1 +{1:"val_468"} 1 +{1:"val_469"} 1 +{1:"val_469"} 1 +{1:"val_469"} 1 +{1:"val_469"} 1 +{1:"val_469"} 1 +{1:"val_47"} 1 +{1:"val_470"} 1 +{1:"val_472"} 1 +{1:"val_475"} 1 +{1:"val_477"} 1 +{1:"val_478"} 1 +{1:"val_478"} 1 +{1:"val_479"} 1 +{1:"val_480"} 1 +{1:"val_480"} 1 +{1:"val_480"} 1 +{1:"val_481"} 1 +{1:"val_482"} 1 +{1:"val_483"} 1 +{1:"val_484"} 1 +{1:"val_485"} 1 +{1:"val_487"} 1 +{1:"val_489"} 1 +{1:"val_489"} 1 +{1:"val_489"} 1 +{1:"val_489"} 1 +{1:"val_490"} 1 +{1:"val_491"} 1 +{1:"val_492"} 1 +{1:"val_492"} 1 +{1:"val_493"} 1 +{1:"val_494"} 1 +{1:"val_495"} 1 +{1:"val_496"} 1 +{1:"val_497"} 1 +{1:"val_498"} 1 +{1:"val_498"} 1 +{1:"val_498"} 1 +{1:"val_5"} 1 +{1:"val_5"} 1 +{1:"val_5"} 1 +{1:"val_51"} 1 +{1:"val_51"} 1 +{1:"val_53"} 1 +{1:"val_54"} 1 +{1:"val_57"} 1 +{1:"val_58"} 1 +{1:"val_58"} 1 +{1:"val_64"} 1 +{1:"val_65"} 1 +{1:"val_66"} 1 +{1:"val_67"} 1 +{1:"val_67"} 1 +{1:"val_69"} 1 +{1:"val_70"} 1 +{1:"val_70"} 1 +{1:"val_70"} 1 +{1:"val_72"} 1 +{1:"val_72"} 1 +{1:"val_74"} 1 +{1:"val_76"} 1 +{1:"val_76"} 1 +{1:"val_77"} 1 +{1:"val_78"} 1 +{1:"val_8"} 1 +{1:"val_80"} 1 +{1:"val_82"} 1 +{1:"val_83"} 1 +{1:"val_83"} 1 +{1:"val_84"} 1 +{1:"val_84"} 1 +{1:"val_85"} 1 +{1:"val_86"} 1 +{1:"val_87"} 1 +{1:"val_9"} 1 +{1:"val_90"} 1 +{1:"val_90"} 1 +{1:"val_90"} 1 +{1:"val_92"} 1 +{1:"val_95"} 1 +{1:"val_95"} 1 +{1:"val_96"} 1 +{1:"val_97"} 1 +{1:"val_97"} 1 +{1:"val_98"} 1 +{1:"val_98"} 1 diff --git ql/src/test/results/clientpositive/orc_int_type_promotion.q.out ql/src/test/results/clientpositive/llap/orc_int_type_promotion.q.out similarity index 86% rename from ql/src/test/results/clientpositive/orc_int_type_promotion.q.out rename to ql/src/test/results/clientpositive/llap/orc_int_type_promotion.q.out index e5a04657b5..14bfd5b97e 100644 --- ql/src/test/results/clientpositive/orc_int_type_promotion.q.out +++ ql/src/test/results/clientpositive/llap/orc_int_type_promotion.q.out @@ -126,8 +126,8 @@ POSTHOOK: query: select * from alltypes_orc_n0 POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypes_orc_n0 #### A masked pattern was here #### -true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k1":"v1","k2":"v2"} [100,200] {"c1":null,"c2":" \"foo\"}"} false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k3":"v3","k4":"v4"} [200,300] {"c1":null,"c2":" \"bar\"}"} +true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k1":"v1","k2":"v2"} [100,200] {"c1":null,"c2":" \"foo\"}"} PREHOOK: query: alter table alltypes_orc_n0 change si si int PREHOOK: type: ALTERTABLE_RENAMECOL PREHOOK: Input: default@alltypes_orc_n0 @@ -144,8 +144,8 @@ POSTHOOK: query: select * from alltypes_orc_n0 POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypes_orc_n0 #### A masked pattern was here #### -true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k1":"v1","k2":"v2"} [100,200] {"c1":null,"c2":" \"foo\"}"} false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k3":"v3","k4":"v4"} [200,300] {"c1":null,"c2":" \"bar\"}"} +true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k1":"v1","k2":"v2"} [100,200] {"c1":null,"c2":" \"foo\"}"} PREHOOK: query: alter table alltypes_orc_n0 change si si bigint PREHOOK: type: ALTERTABLE_RENAMECOL PREHOOK: Input: default@alltypes_orc_n0 @@ -170,8 +170,8 @@ POSTHOOK: query: select * from alltypes_orc_n0 POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypes_orc_n0 #### A masked pattern was here #### -true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k1":"v1","k2":"v2"} [100,200] {"c1":null,"c2":" \"foo\"}"} false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k3":"v3","k4":"v4"} [200,300] {"c1":null,"c2":" \"bar\"}"} +true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k1":"v1","k2":"v2"} [100,200] {"c1":null,"c2":" \"foo\"}"} PREHOOK: query: explain select ti, si, i, bi from alltypes_orc_n0 PREHOOK: type: QUERY PREHOOK: Input: default@alltypes_orc_n0 @@ -186,23 +186,27 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypes_orc_n0 - Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ti (type: tinyint), si (type: bigint), i (type: bigint), bi (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypes_orc_n0 + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ti (type: tinyint), si (type: bigint), i (type: bigint), bi (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 56 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs Stage: Stage-0 Fetch Operator @@ -249,28 +253,28 @@ POSTHOOK: Lineage: src_part_orc PARTITION(ds=2008-04-08).key EXPRESSION [(srcpar POSTHOOK: Lineage: src_part_orc PARTITION(ds=2008-04-08).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src_part_orc PARTITION(ds=2008-04-09).key EXPRESSION [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src_part_orc PARTITION(ds=2008-04-09).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_part_orc limit 10 +PREHOOK: query: select * from src_part_orc order by key, value limit 10 PREHOOK: type: QUERY PREHOOK: Input: default@src_part_orc PREHOOK: Input: default@src_part_orc@ds=2008-04-08 PREHOOK: Input: default@src_part_orc@ds=2008-04-09 #### A masked pattern was here #### -POSTHOOK: query: select * from src_part_orc limit 10 +POSTHOOK: query: select * from src_part_orc order by key, value limit 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@src_part_orc POSTHOOK: Input: default@src_part_orc@ds=2008-04-08 POSTHOOK: Input: default@src_part_orc@ds=2008-04-09 #### A masked pattern was here #### -238 val_238 2008-04-08 -97 val_97 2008-04-08 -200 val_200 2008-04-08 -400 val_400 2008-04-08 -403 val_403 2008-04-08 -169 val_169 2008-04-08 -90 val_90 2008-04-08 -126 val_126 2008-04-08 -222 val_222 2008-04-08 -477 val_477 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-09 +0 val_0 2008-04-09 +0 val_0 2008-04-09 +0 val_0 2008-04-09 +0 val_0 2008-04-09 PREHOOK: query: alter table src_part_orc change key key bigint PREHOOK: type: ALTERTABLE_RENAMECOL PREHOOK: Input: default@src_part_orc @@ -279,25 +283,25 @@ POSTHOOK: query: alter table src_part_orc change key key bigint POSTHOOK: type: ALTERTABLE_RENAMECOL POSTHOOK: Input: default@src_part_orc POSTHOOK: Output: default@src_part_orc -PREHOOK: query: select * from src_part_orc limit 10 +PREHOOK: query: select * from src_part_orc order by key, value limit 10 PREHOOK: type: QUERY PREHOOK: Input: default@src_part_orc PREHOOK: Input: default@src_part_orc@ds=2008-04-08 PREHOOK: Input: default@src_part_orc@ds=2008-04-09 #### A masked pattern was here #### -POSTHOOK: query: select * from src_part_orc limit 10 +POSTHOOK: query: select * from src_part_orc order by key, value limit 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@src_part_orc POSTHOOK: Input: default@src_part_orc@ds=2008-04-08 POSTHOOK: Input: default@src_part_orc@ds=2008-04-09 #### A masked pattern was here #### -238 val_238 2008-04-08 -97 val_97 2008-04-08 -200 val_200 2008-04-08 -400 val_400 2008-04-08 -403 val_403 2008-04-08 -169 val_169 2008-04-08 -90 val_90 2008-04-08 -126 val_126 2008-04-08 -222 val_222 2008-04-08 -477 val_477 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-08 +0 val_0 2008-04-09 +0 val_0 2008-04-09 +0 val_0 2008-04-09 +0 val_0 2008-04-09 +0 val_0 2008-04-09 diff --git ql/src/test/results/clientpositive/llap/orc_nested_column_pruning.q.out ql/src/test/results/clientpositive/llap/orc_nested_column_pruning.q.out new file mode 100644 index 0000000000..a20ead8e68 --- /dev/null +++ ql/src/test/results/clientpositive/llap/orc_nested_column_pruning.q.out @@ -0,0 +1,2205 @@ +PREHOOK: query: DROP TABLE IF EXISTS dummy_n4 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS dummy_n4 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE dummy_n4 (i int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dummy_n4 +POSTHOOK: query: CREATE TABLE dummy_n4 (i int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dummy_n4 +PREHOOK: query: INSERT INTO TABLE dummy_n4 VALUES (42) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@dummy_n4 +POSTHOOK: query: INSERT INTO TABLE dummy_n4 VALUES (42) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@dummy_n4 +POSTHOOK: Lineage: dummy_n4.i SCRIPT [] +PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE nested_tbl_1_n0 ( + a int, + s1 struct, f6: int>, + s2 struct, f11: map>>, + s3 struct>>, + s4 map>, + s5 struct>>>, + s6 map>>>> +) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nested_tbl_1_n0 +POSTHOOK: query: CREATE TABLE nested_tbl_1_n0 ( + a int, + s1 struct, f6: int>, + s2 struct, f11: map>>, + s3 struct>>, + s4 map>, + s5 struct>>>, + s6 map>>>> +) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nested_tbl_1_n0 +PREHOOK: query: INSERT INTO TABLE nested_tbl_1_n0 SELECT + 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), + named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), + named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), + map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), + named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), + map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), + 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) +FROM dummy_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@dummy_n4 +PREHOOK: Output: default@nested_tbl_1_n0 +POSTHOOK: query: INSERT INTO TABLE nested_tbl_1_n0 SELECT + 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), + named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), + named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), + map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), + named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), + map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), + 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) +FROM dummy_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dummy_n4 +POSTHOOK: Output: default@nested_tbl_1_n0 +POSTHOOK: Lineage: nested_tbl_1_n0.a SIMPLE [] +POSTHOOK: Lineage: nested_tbl_1_n0.s1 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n0.s2 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n0.s3 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n0.s4 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n0.s5 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_1_n0.s6 EXPRESSION [] +PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE nested_tbl_2_n0 LIKE nested_tbl_1_n0 +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nested_tbl_2_n0 +POSTHOOK: query: CREATE TABLE nested_tbl_2_n0 LIKE nested_tbl_1_n0 +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nested_tbl_2_n0 +PREHOOK: query: INSERT INTO TABLE nested_tbl_2_n0 SELECT + 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), + named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), + named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), + map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), + named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), + map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), + 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) +FROM dummy_n4 +PREHOOK: type: QUERY +PREHOOK: Input: default@dummy_n4 +PREHOOK: Output: default@nested_tbl_2_n0 +POSTHOOK: query: INSERT INTO TABLE nested_tbl_2_n0 SELECT + 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), + named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), + named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), + map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), + named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), + map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), + 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) +FROM dummy_n4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dummy_n4 +POSTHOOK: Output: default@nested_tbl_2_n0 +POSTHOOK: Lineage: nested_tbl_2_n0.a SIMPLE [] +POSTHOOK: Lineage: nested_tbl_2_n0.s1 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n0.s2 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n0.s3 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n0.s4 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n0.s5 EXPRESSION [] +POSTHOOK: Lineage: nested_tbl_2_n0.s6 EXPRESSION [] +PREHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +1 +PREHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f1 (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +false +PREHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f1, s1.f2 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f1 (type: boolean), s1.f2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +false foo +PREHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f3 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +{"f4":4,"f5":5.0} 4 +PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f3.f5 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +5.0 +PREHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f3.f4, s2.f8.f9 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f4 (type: int), s2.f8.f9 (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +4 true +PREHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + filterExpr: (not s1.f1) (type: boolean) + Pruned Column Paths: s1.f2, s1.f1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (not s1.f1) (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f2 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +foo +PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + filterExpr: (s1.f3.f4 = 4) (type: boolean) + Pruned Column Paths: s1.f3.f5, s1.f3.f4 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f3.f4 = 4) (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +5.0 +PREHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + filterExpr: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) + Pruned Column Paths: s1.f2, s2.f8 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s2.f8 (type: struct,f11:map>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +{"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} +PREHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n0 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n0 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s2.f8.f10 + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s3 (type: struct>>) + outputColumnNames: s3 + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col3, _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int) + outputColumnNames: _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col3.f12 (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: s2.f8.f10 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col3, _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int) + outputColumnNames: _col10 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col3.f12 (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col10, _col11 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col10 (type: int), _col11 (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n0 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n0 +LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 +LATERAL VIEW explode(s3.f12) tbl2 AS col2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +10 {"f13":"foo","f14":14} +10 {"f13":"bar","f14":28} +11 {"f13":"foo","f14":14} +11 {"f13":"bar","f14":28} +PREHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s2.f8.f10, s1.f3.f4 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (s2.f8.f10[1] pmod s1.f3.f4) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +3 +PREHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f3.f5, s1.f3.f4 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3.f5 (type: double), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: double) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +5.0 1 +PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f3 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: struct) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: struct) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: struct) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +{"f4":4,"f5":5.0} 1 +PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f3 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: struct) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: struct) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: struct) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: struct) + null sort order: z + sort order: + + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +{"f4":4,"f5":5.0} 1 +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +PREHOOK: Input: default@nested_tbl_2_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +POSTHOOK: Input: default@nested_tbl_2_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f3.f4 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f3.f4 (type: int) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f6 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f6 (type: int) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0.f3.f4 (type: int) + 1 _col0.f6 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +PREHOOK: Input: default@nested_tbl_2_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == FALSE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +POSTHOOK: Input: default@nested_tbl_2_n0 +#### A masked pattern was here #### +5.0 {"f9":false,"f10":[20,22],"f11":{"key3":true,"key4":false}} +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f3.f4 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f3.f4 (type: int) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (s1.f6 is not null and s2.f8.f9) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f6 is not null and s2.f8.f9) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0.f6 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0.f6 (type: int) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0.f3.f4 (type: int) + 1 _col0.f6 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 +FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 +WHERE t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +5.0 {"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), true (type: boolean) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: int), true (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) + Pruned Column Paths: s1.f6, s2.f8.f9 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1.f6 (type: int), s2.f8.f9 (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: int), _col1 (type: boolean) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: boolean) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: int), true (type: boolean) + 1 _col0 (type: int), _col1 (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +5.0 +Warning: Shuffle Join MERGEJOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 3 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: t2 + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s2 (type: struct,f11:map>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + residual filter predicates: {(_col0.f1 <> _col1.f8.f9)} + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +5.0 +PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f3.f4 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f6:int>) + Execution mode: llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: s1.f6 is not null (type: boolean) + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s1.f6 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s2 (type: struct,f11:map>>), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct,f11:map>>) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col2 + residual filter predicates: {(_col0.f1 <> _col2.f8.f9)} + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0.f3.f5 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.s1.f3.f5 +FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 +ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +5.0 +PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE nested_tbl_3_n0 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nested_tbl_3_n0 +POSTHOOK: query: CREATE TABLE nested_tbl_3_n0 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nested_tbl_3_n0 +PREHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n0 PARTITION(f3) +SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 +FROM nested_tbl_1_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +PREHOOK: Output: default@nested_tbl_3_n0 +POSTHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n0 PARTITION(f3) +SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 +FROM nested_tbl_1_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +POSTHOOK: Output: default@nested_tbl_3_n0@f3=4 +POSTHOOK: Lineage: nested_tbl_3_n0 PARTITION(f3=4).f1 EXPRESSION [(nested_tbl_1_n0)nested_tbl_1_n0.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] +POSTHOOK: Lineage: nested_tbl_3_n0 PARTITION(f3=4).f2 EXPRESSION [(nested_tbl_1_n0)nested_tbl_1_n0.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] +PREHOOK: query: SELECT * FROM nested_tbl_3_n0 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_3_n0 +PREHOOK: Input: default@nested_tbl_3_n0@f3=4 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM nested_tbl_3_n0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_3_n0 +POSTHOOK: Input: default@nested_tbl_3_n0@f3=4 +#### A masked pattern was here #### +false foo 4 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n0 +GROUP BY s3.f12[0].f14 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n0 +GROUP BY s3.f12[0].f14 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s3.f12, s1.f6 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s3.f12[0].f14 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n0 +GROUP BY s3.f12[0].f14 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 +FROM nested_tbl_1_n0 +GROUP BY s3.f12[0].f14 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +1 14 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n0 +GROUP BY s4['key1'].f15 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n0 +GROUP BY s4['key1'].f15 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s4['key1'].f15 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n0 +GROUP BY s4['key1'].f15 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s4['key1'].f15 +FROM nested_tbl_1_n0 +GROUP BY s4['key1'].f15 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +1 1 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16[0].f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16[0].f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s5.f16, s1.f6 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s5.f16[0].f18.f19 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16[0].f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16[0].f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +1 14 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16.f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16.f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f6, s5.f16 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s5 (type: struct>>>) + outputColumnNames: s1, s5 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(s1.f6) + keys: s5.f16.f18.f19 (type: array) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: array) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: array) + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: array) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: array) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16.f18.f19 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 +FROM nested_tbl_1_n0 +GROUP BY s5.f16.f18.f19 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +1 [14,28] +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20[0].f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20[0].f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s6['key1'].f20[0].f21.f22 (type: int), s1.f6 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20[0].f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20[0].f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +1 1 +PREHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20.f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20.f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: nested_tbl_1_n0 + Pruned Column Paths: s1.f6 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s1 (type: struct,f6:int>), s6 (type: map>>>>) + outputColumnNames: s1, s6 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(s1.f6) + keys: s6['key1'].f20.f21.f22 (type: array) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: array) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: array) + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: array) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: array) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20.f21.f22 +PREHOOK: type: QUERY +PREHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 +FROM nested_tbl_1_n0 +GROUP BY s6['key1'].f20.f21.f22 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nested_tbl_1_n0 +#### A masked pattern was here #### +1 [1] diff --git ql/src/test/results/clientpositive/orc_ppd_str_conversion.q.out ql/src/test/results/clientpositive/llap/orc_ppd_str_conversion.q.out similarity index 71% rename from ql/src/test/results/clientpositive/orc_ppd_str_conversion.q.out rename to ql/src/test/results/clientpositive/llap/orc_ppd_str_conversion.q.out index c0679916d7..8f9d633926 100644 --- ql/src/test/results/clientpositive/orc_ppd_str_conversion.q.out +++ ql/src/test/results/clientpositive/llap/orc_ppd_str_conversion.q.out @@ -43,37 +43,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@text_test #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: text_test - filterExpr: (col2 = '1 ') (type: boolean) - Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (col2 = '1 ') (type: boolean) - Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: col1 (type: varchar(15)), '1 ' (type: char(10)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 173 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: text_test + filterExpr: (col2 = '1 ') (type: boolean) + Filter Operator + predicate: (col2 = '1 ') (type: boolean) + Select Operator + expressions: col1 (type: varchar(15)), '1 ' (type: char(10)) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: select * from text_test where col2='1' PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/orc_schema_evolution_float.q.out ql/src/test/results/clientpositive/llap/orc_schema_evolution_float.q.out similarity index 99% rename from ql/src/test/results/clientpositive/orc_schema_evolution_float.q.out rename to ql/src/test/results/clientpositive/llap/orc_schema_evolution_float.q.out index 21761230ee..6299ea6269 100644 --- ql/src/test/results/clientpositive/orc_schema_evolution_float.q.out +++ ql/src/test/results/clientpositive/llap/orc_schema_evolution_float.q.out @@ -100,7 +100,7 @@ POSTHOOK: query: select f from float_text where f=74.72 POSTHOOK: type: QUERY POSTHOOK: Input: default@float_text #### A masked pattern was here #### -74.72000 +74.72 PREHOOK: query: select f from float_text where f=0.22 PREHOOK: type: QUERY PREHOOK: Input: default@float_text @@ -109,7 +109,7 @@ POSTHOOK: query: select f from float_text where f=0.22 POSTHOOK: type: QUERY POSTHOOK: Input: default@float_text #### A masked pattern was here #### -0.22000 +0.22 PREHOOK: query: create table float_orc(f float) stored as orc PREHOOK: type: CREATETABLE PREHOOK: Output: database:default @@ -217,7 +217,7 @@ POSTHOOK: query: select f from float_orc where f=74.72 POSTHOOK: type: QUERY POSTHOOK: Input: default@float_orc #### A masked pattern was here #### -74.72000 +74.72 PREHOOK: query: select f from float_orc where f=0.22 PREHOOK: type: QUERY PREHOOK: Input: default@float_orc @@ -226,7 +226,7 @@ POSTHOOK: query: select f from float_orc where f=0.22 POSTHOOK: type: QUERY POSTHOOK: Input: default@float_orc #### A masked pattern was here #### -0.22000 +0.22 PREHOOK: query: select f from float_orc where f=74.72 PREHOOK: type: QUERY PREHOOK: Input: default@float_orc @@ -235,7 +235,7 @@ POSTHOOK: query: select f from float_orc where f=74.72 POSTHOOK: type: QUERY POSTHOOK: Input: default@float_orc #### A masked pattern was here #### -74.72000 +74.72 PREHOOK: query: select f from float_orc where f=0.22 PREHOOK: type: QUERY PREHOOK: Input: default@float_orc @@ -244,7 +244,7 @@ POSTHOOK: query: select f from float_orc where f=0.22 POSTHOOK: type: QUERY POSTHOOK: Input: default@float_orc #### A masked pattern was here #### -0.22000 +0.22 PREHOOK: query: drop table float_text PREHOOK: type: DROPTABLE PREHOOK: Input: default@float_text diff --git ql/src/test/results/clientpositive/llap/order.q.out ql/src/test/results/clientpositive/llap/order.q.out new file mode 100644 index 0000000000..dc65671238 --- /dev/null +++ ql/src/test/results/clientpositive/llap/order.q.out @@ -0,0 +1,176 @@ +PREHOOK: query: EXPLAIN +SELECT x.* FROM SRC x ORDER BY key limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT x.* FROM SRC x ORDER BY key limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: string) + null sort order: z + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 10 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT x.* FROM SRC x ORDER BY key limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT x.* FROM SRC x ORDER BY key limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +10 val_10 +100 val_100 +100 val_100 +103 val_103 +103 val_103 +104 val_104 +104 val_104 +PREHOOK: query: EXPLAIN +SELECT x.* FROM SRC x ORDER BY key desc limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT x.* FROM SRC x ORDER BY key desc limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: - + keys: key (type: string) + null sort order: z + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 10 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: - + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT x.* FROM SRC x ORDER BY key desc limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT x.* FROM SRC x ORDER BY key desc limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +98 val_98 +98 val_98 +97 val_97 +97 val_97 +96 val_96 +95 val_95 +95 val_95 +92 val_92 +90 val_90 +90 val_90 diff --git ql/src/test/results/clientpositive/llap/order3.q.out ql/src/test/results/clientpositive/llap/order3.q.out new file mode 100644 index 0000000000..96eec99510 --- /dev/null +++ ql/src/test/results/clientpositive/llap/order3.q.out @@ -0,0 +1,657 @@ +PREHOOK: query: drop table if exists test_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists test_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table test_n0(key int, value1 int, value2 string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test_n0 +POSTHOOK: query: create table test_n0(key int, value1 int, value2 string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_n0 +PREHOOK: query: insert into table test_n0 values (1, 1, 'val111'), (1, 2, 'val121'), (1, 3, 'val131'), (2, 1, 'val211'), (2, 2, 'val221'), (2, 2, 'val222'), (2, 3, 'val231'), (2, 4, 'val241'), +(3, 1, 'val311'), (3, 2, 'val321'), (3, 2, 'val322'), (3, 3, 'val331'), (3, 3, 'val332'), (3, 3, 'val333'), (4, 1, 'val411') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@test_n0 +POSTHOOK: query: insert into table test_n0 values (1, 1, 'val111'), (1, 2, 'val121'), (1, 3, 'val131'), (2, 1, 'val211'), (2, 2, 'val221'), (2, 2, 'val222'), (2, 3, 'val231'), (2, 4, 'val241'), +(3, 1, 'val311'), (3, 2, 'val321'), (3, 2, 'val322'), (3, 3, 'val331'), (3, 3, 'val332'), (3, 3, 'val333'), (4, 1, 'val411') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@test_n0 +POSTHOOK: Lineage: test_n0.key SCRIPT [] +POSTHOOK: Lineage: test_n0.value1 SCRIPT [] +POSTHOOK: Lineage: test_n0.value2 SCRIPT [] +PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: int) + null sort order: z + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: int) + minReductionHashAggr: 0.73333335 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +1 +2 +3 +PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: int) + null sort order: z + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Select Operator + expressions: key (type: int), value1 (type: int) + outputColumnNames: key, value1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(value1) + keys: key (type: int) + minReductionHashAggr: 0.73333335 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), _col0 (type: int) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + null sort order: z + sort order: + + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: int) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +1 3 +2 4 +3 3 +PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: int) + null sort order: z + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Select Operator + expressions: key (type: int), value1 (type: int) + outputColumnNames: key, value1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value1) + keys: key (type: int) + minReductionHashAggr: 0.73333335 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: int) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + null sort order: z + sort order: + + Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), 'AAA' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + ListSink + +PREHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +1 3 AAA +2 5 AAA +3 6 AAA +PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: int) + null sort order: z + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: int) + minReductionHashAggr: 0.73333335 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + ListSink + +PREHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +1 +2 +3 +PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: int) + null sort order: z + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Select Operator + expressions: key (type: int), value1 (type: int) + outputColumnNames: key, value1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(value1) + keys: key (type: int) + minReductionHashAggr: 0.73333335 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: int) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + ListSink + +PREHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +1 3 +2 4 +3 3 +PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: int) + null sort order: z + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Select Operator + expressions: key (type: int), value1 (type: int) + outputColumnNames: key, value1 + Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value1) + keys: key (type: int), 'AAA' (type: string) + minReductionHashAggr: 0.73333335 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), 'AAA' (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), 'AAA' (type: string) + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), 'AAA' (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col2 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), 'AAA' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + ListSink + +PREHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_n0 +#### A masked pattern was here #### +POSTHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_n0 +#### A masked pattern was here #### +1 3 AAA +2 5 AAA +3 6 AAA diff --git ql/src/test/results/clientpositive/order_by_expr_1.q.out ql/src/test/results/clientpositive/llap/order_by_expr_1.q.out similarity index 72% rename from ql/src/test/results/clientpositive/order_by_expr_1.q.out rename to ql/src/test/results/clientpositive/llap/order_by_expr_1.q.out index 7dc3344877..b6462a7b69 100644 --- ql/src/test/results/clientpositive/order_by_expr_1.q.out +++ ql/src/test/results/clientpositive/llap/order_by_expr_1.q.out @@ -57,26 +57,30 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t_n5 - Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: INTERVAL'5-5' (type: interval_year_month), INTERVAL'-1-1' (type: interval_year_month) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 2 - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t_n5 + Statistics: Num rows: 9 Data size: 37 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: INTERVAL'5-5' (type: interval_year_month), INTERVAL'-1-1' (type: interval_year_month) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 2 + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs Stage: Stage-0 Fetch Operator @@ -317,34 +321,43 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t_n5 - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: b (type: int), (0 - b) (type: int), (a + 1) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int) - null sort order: zz - sort order: ++ - Statistics: Num rows: 9 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t_n5 + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: b (type: int), (0 - b) (type: int), (a + 1) (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 9 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + null sort order: zz + sort order: ++ + Statistics: Num rows: 9 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -485,34 +498,43 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t_n5 - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int), b (type: int), (2 * b) (type: int), (a + 1) (type: int), (0 - b) (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col5 - Statistics: Num rows: 9 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col4 (type: int), _col5 (type: int) - null sort order: zzz - sort order: +++ - Statistics: Num rows: 9 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int), _col3 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t_n5 + Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: a (type: int), b (type: int), (2 * b) (type: int), (a + 1) (type: int), (0 - b) (type: int) + outputColumnNames: _col0, _col2, _col3, _col4, _col5 + Statistics: Num rows: 9 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col4 (type: int), _col5 (type: int) + null sort order: zzz + sort order: +++ + Statistics: Num rows: 9 Data size: 216 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col3 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/order_by_expr_2.q.out ql/src/test/results/clientpositive/llap/order_by_expr_2.q.out similarity index 92% rename from ql/src/test/results/clientpositive/order_by_expr_2.q.out rename to ql/src/test/results/clientpositive/llap/order_by_expr_2.q.out index 66ac0bb7cf..a76cc11943 100644 --- ql/src/test/results/clientpositive/order_by_expr_2.q.out +++ ql/src/test/results/clientpositive/llap/order_by_expr_2.q.out @@ -16,11 +16,11 @@ POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@t_n14 POSTHOOK: Lineage: t_n14.a SCRIPT [] POSTHOOK: Lineage: t_n14.b SCRIPT [] -PREHOOK: query: select a as b, b as a from t_n14 order by a +PREHOOK: query: select a as b, b as a from t_n14 order by a, b PREHOOK: type: QUERY PREHOOK: Input: default@t_n14 #### A masked pattern was here #### -POSTHOOK: query: select a as b, b as a from t_n14 order by a +POSTHOOK: query: select a as b, b as a from t_n14 order by a, b POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n14 #### A masked pattern was here #### @@ -33,18 +33,18 @@ POSTHOOK: Input: default@t_n14 3 7 8 9 -1000 100 -PREHOOK: query: select a as b, b as a from t_n14 order by t_n14.a +PREHOOK: query: select a as b, b as a from t_n14 order by t_n14.a, t_n14.b PREHOOK: type: QUERY PREHOOK: Input: default@t_n14 #### A masked pattern was here #### -POSTHOOK: query: select a as b, b as a from t_n14 order by t_n14.a +POSTHOOK: query: select a as b, b as a from t_n14 order by t_n14.a, t_n14.b POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n14 #### A masked pattern was here #### -1000 100 -1 3 1 2 1 2 +1 3 2 4 3 7 4 5 @@ -84,11 +84,11 @@ POSTHOOK: Input: default@t_n14 1 1 -1000 -PREHOOK: query: select a,b,count(*),a+b from t_n14 group by a, b order by a+b +PREHOOK: query: select a,b,count(*),a+b from t_n14 group by a, b order by a+b, a PREHOOK: type: QUERY PREHOOK: Input: default@t_n14 #### A masked pattern was here #### -POSTHOOK: query: select a,b,count(*),a+b from t_n14 group by a, b order by a+b +POSTHOOK: query: select a,b,count(*),a+b from t_n14 group by a, b order by a+b, a POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n14 #### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/order_by_pos.q.out ql/src/test/results/clientpositive/llap/order_by_pos.q.out similarity index 90% rename from ql/src/test/results/clientpositive/order_by_pos.q.out rename to ql/src/test/results/clientpositive/llap/order_by_pos.q.out index e79149c78c..496e5b3386 100644 --- ql/src/test/results/clientpositive/order_by_pos.q.out +++ ql/src/test/results/clientpositive/llap/order_by_pos.q.out @@ -16,11 +16,11 @@ POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@t_n3 POSTHOOK: Lineage: t_n3.a SCRIPT [] POSTHOOK: Lineage: t_n3.b SCRIPT [] -PREHOOK: query: select * from t_n3 order by 2 +PREHOOK: query: select * from t_n3 order by 2, 1 PREHOOK: type: QUERY PREHOOK: Input: default@t_n3 #### A masked pattern was here #### -POSTHOOK: query: select * from t_n3 order by 2 +POSTHOOK: query: select * from t_n3 order by 2, 1 POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n3 #### A masked pattern was here #### @@ -33,18 +33,18 @@ POSTHOOK: Input: default@t_n3 3 7 8 9 -1000 100 -PREHOOK: query: select * from t_n3 order by 1 +PREHOOK: query: select * from t_n3 order by 1, 2 PREHOOK: type: QUERY PREHOOK: Input: default@t_n3 #### A masked pattern was here #### -POSTHOOK: query: select * from t_n3 order by 1 +POSTHOOK: query: select * from t_n3 order by 1, 2 POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n3 #### A masked pattern was here #### -1000 100 -1 3 1 2 1 2 +1 3 2 4 3 7 4 5 @@ -66,11 +66,11 @@ POSTHOOK: Input: default@t_n3 4 5 8 9 20 -100 -PREHOOK: query: select * from t_n3 union select * from t_n3 order by 2 +PREHOOK: query: select * from t_n3 union select * from t_n3 order by 2, 1 PREHOOK: type: QUERY PREHOOK: Input: default@t_n3 #### A masked pattern was here #### -POSTHOOK: query: select * from t_n3 union select * from t_n3 order by 2 +POSTHOOK: query: select * from t_n3 union select * from t_n3 order by 2, 1 POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n3 #### A masked pattern was here #### @@ -82,17 +82,17 @@ POSTHOOK: Input: default@t_n3 3 7 8 9 -1000 100 -PREHOOK: query: select * from t_n3 union select * from t_n3 order by 1 +PREHOOK: query: select * from t_n3 union select * from t_n3 order by 1, 2 PREHOOK: type: QUERY PREHOOK: Input: default@t_n3 #### A masked pattern was here #### -POSTHOOK: query: select * from t_n3 union select * from t_n3 order by 1 +POSTHOOK: query: select * from t_n3 union select * from t_n3 order by 1, 2 POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n3 #### A masked pattern was here #### -1000 100 -1 3 1 2 +1 3 2 4 3 7 4 5 @@ -113,11 +113,11 @@ POSTHOOK: Input: default@t_n3 8 1 20 1 1 3 -PREHOOK: query: select * from (select a,b, count(*) from t_n3 group by a, b)subq order by 3, 2 desc +PREHOOK: query: select * from (select a,b, count(*) from t_n3 group by a, b)subq order by 3, 2 desc, 1 PREHOOK: type: QUERY PREHOOK: Input: default@t_n3 #### A masked pattern was here #### -POSTHOOK: query: select * from (select a,b, count(*) from t_n3 group by a, b)subq order by 3, 2 desc +POSTHOOK: query: select * from (select a,b, count(*) from t_n3 group by a, b)subq order by 3, 2 desc, 1 POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n3 #### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/llap/outer_join_ppr.q.out ql/src/test/results/clientpositive/llap/outer_join_ppr.q.out new file mode 100644 index 0000000000..d7bc092156 --- /dev/null +++ ql/src/test/results/clientpositive/llap/outer_join_ppr.q.out @@ -0,0 +1,684 @@ +PREHOOK: query: EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`src` +WHERE `key` < 20 AND `key` > 15) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`srcpart` +WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +17 val_17 17 val_17 +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 +PREHOOK: query: EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED + FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`src` +WHERE `key` < 20 AND `key` > 15) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`srcpart` +WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: FROM + src a + FULL OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +17 val_17 17 val_17 +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 diff --git ql/src/test/results/clientpositive/llap/outer_reference_windowed.q.out ql/src/test/results/clientpositive/llap/outer_reference_windowed.q.out new file mode 100644 index 0000000000..d3d8d820eb --- /dev/null +++ ql/src/test/results/clientpositive/llap/outer_reference_windowed.q.out @@ -0,0 +1,938 @@ +PREHOOK: query: DROP TABLE IF EXISTS e011_01 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS e011_01 +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE IF EXISTS e011_02 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS e011_02 +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE IF EXISTS e011_03 +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS e011_03 +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE e011_01 ( + c1 decimal(15,2), + c2 decimal(15,2)) + STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e011_01 +POSTHOOK: query: CREATE TABLE e011_01 ( + c1 decimal(15,2), + c2 decimal(15,2)) + STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e011_01 +PREHOOK: query: CREATE TABLE e011_02 ( + c1 decimal(15,2), + c2 decimal(15,2)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e011_02 +POSTHOOK: query: CREATE TABLE e011_02 ( + c1 decimal(15,2), + c2 decimal(15,2)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e011_02 +PREHOOK: query: CREATE TABLE e011_03 ( + c1 decimal(15,2), + c2 decimal(15,2)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@e011_03 +POSTHOOK: query: CREATE TABLE e011_03 ( + c1 decimal(15,2), + c2 decimal(15,2)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@e011_03 +PREHOOK: query: LOAD DATA + LOCAL INPATH '../../data/files/e011_01.txt' + OVERWRITE + INTO TABLE e011_01 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@e011_01 +POSTHOOK: query: LOAD DATA + LOCAL INPATH '../../data/files/e011_01.txt' + OVERWRITE + INTO TABLE e011_01 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@e011_01 +PREHOOK: query: INSERT INTO TABLE e011_02 + SELECT c1, c2 + FROM e011_01 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Output: default@e011_02 +POSTHOOK: query: INSERT INTO TABLE e011_02 + SELECT c1, c2 + FROM e011_01 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Output: default@e011_02 +POSTHOOK: Lineage: e011_02.c1 SIMPLE [(e011_01)e011_01.FieldSchema(name:c1, type:decimal(15,2), comment:null), ] +POSTHOOK: Lineage: e011_02.c2 SIMPLE [(e011_01)e011_01.FieldSchema(name:c2, type:decimal(15,2), comment:null), ] +PREHOOK: query: INSERT INTO TABLE e011_03 + SELECT c1, c2 + FROM e011_01 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Output: default@e011_03 +POSTHOOK: query: INSERT INTO TABLE e011_03 + SELECT c1, c2 + FROM e011_01 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Output: default@e011_03 +POSTHOOK: Lineage: e011_03.c1 SIMPLE [(e011_01)e011_01.FieldSchema(name:c1, type:decimal(15,2), comment:null), ] +POSTHOOK: Lineage: e011_03.c2 SIMPLE [(e011_01)e011_01.FieldSchema(name:c2, type:decimal(15,2), comment:null), ] +PREHOOK: query: ANALYZE TABLE e011_01 COMPUTE STATISTICS FOR COLUMNS +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@e011_01 +PREHOOK: Output: default@e011_01 +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE TABLE e011_01 COMPUTE STATISTICS FOR COLUMNS +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@e011_01 +POSTHOOK: Output: default@e011_01 +#### A masked pattern was here #### +PREHOOK: query: ANALYZE TABLE e011_02 COMPUTE STATISTICS FOR COLUMNS +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@e011_02 +PREHOOK: Output: default@e011_02 +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE TABLE e011_02 COMPUTE STATISTICS FOR COLUMNS +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@e011_02 +POSTHOOK: Output: default@e011_02 +#### A masked pattern was here #### +PREHOOK: query: ANALYZE TABLE e011_03 COMPUTE STATISTICS FOR COLUMNS +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@e011_03 +PREHOOK: Output: default@e011_03 +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE TABLE e011_03 COMPUTE STATISTICS FOR COLUMNS +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@e011_03 +POSTHOOK: Output: default@e011_03 +#### A masked pattern was here #### +PREHOOK: query: describe formatted e011_01 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@e011_01 +POSTHOOK: query: describe formatted e011_01 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@e011_01 +# col_name data_type comment +c1 decimal(15,2) +c2 decimal(15,2) + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"c1\":\"true\",\"c2\":\"true\"}} + bucketing_version 2 + numFiles 1 + numRows 4 + rawDataSize 12 + totalSize 16 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +InputFormat: org.apache.hadoop.mapred.TextInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: explain select sum(sum(c1)) over() from e011_01 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(sum(c1)) over() from e011_01 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: e011_01 + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)) + outputColumnNames: c1 + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(c1) + minReductionHashAggr: 0.75 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(25,2)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 0 (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: 0 (type: int) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(25,2)) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: decimal(25,2)) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: decimal(25,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: 0 ASC NULLS FIRST + partition by: 0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumHiveDecimal + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: decimal(35,2)) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(sum(c1)) over() from e011_01 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +#### A masked pattern was here #### +POSTHOOK: query: select sum(sum(c1)) over() from e011_01 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +#### A masked pattern was here #### +16.00 +PREHOOK: query: explain select sum(sum(c1)) over( + partition by c2 order by c1) + from e011_01 + group by e011_01.c1, e011_01.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(sum(c1)) over( + partition by c2 order by c1) + from e011_01 + group by e011_01.c1, e011_01.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: e011_01 + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) + outputColumnNames: c1, c2 + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(c1) + keys: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(25,2)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) + null sort order: az + sort order: ++ + Map-reduce partition columns: _col1 (type: decimal(15,2)) + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(25,2)) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: decimal(25,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS LAST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col2 + name: sum + window function: GenericUDAFSumHiveDecimal + window frame: RANGE PRECEDING(MAX)~CURRENT + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: decimal(35,2)) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(sum(c1)) over( + partition by c2 order by c1) + from e011_01 + group by e011_01.c1, e011_01.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +#### A masked pattern was here #### +POSTHOOK: query: select sum(sum(c1)) over( + partition by c2 order by c1) + from e011_01 + group by e011_01.c1, e011_01.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +#### A masked pattern was here #### +1.00 +3.00 +5.00 +7.00 +PREHOOK: query: explain select sum(sum(e011_01.c1)) over( + partition by e011_01.c2 order by e011_01.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_01.c1, e011_01.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Input: default@e011_03 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(sum(e011_01.c1)) over( + partition by e011_01.c2 order by e011_01.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_01.c1, e011_01.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Input: default@e011_03 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: e011_01 + filterExpr: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(15,2)) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(15,2)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: e011_03 + filterExpr: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(15,2)) + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: decimal(15,2)) + 1 _col0 (type: decimal(15,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0) + keys: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(25,2)) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) + null sort order: az + sort order: ++ + Map-reduce partition columns: _col1 (type: decimal(15,2)) + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(25,2)) + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: decimal(25,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS LAST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col2 + name: sum + window function: GenericUDAFSumHiveDecimal + window frame: RANGE PRECEDING(MAX)~CURRENT + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: decimal(35,2)) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(sum(e011_01.c1)) over( + partition by e011_01.c2 order by e011_01.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_01.c1, e011_01.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Input: default@e011_03 +#### A masked pattern was here #### +POSTHOOK: query: select sum(sum(e011_01.c1)) over( + partition by e011_01.c2 order by e011_01.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_01.c1, e011_01.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Input: default@e011_03 +#### A masked pattern was here #### +1.00 +3.00 +5.00 +7.00 +PREHOOK: query: explain select sum(sum(e011_01.c1)) over( + partition by e011_03.c2 order by e011_03.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c1, e011_03.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Input: default@e011_03 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(sum(e011_01.c1)) over( + partition by e011_03.c2 order by e011_03.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c1, e011_03.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Input: default@e011_03 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: e011_01 + filterExpr: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(15,2)) + Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: e011_03 + filterExpr: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(15,2)) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(15,2)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: decimal(15,2)) + 1 _col0 (type: decimal(15,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0) + keys: _col1 (type: decimal(15,2)), _col2 (type: decimal(15,2)) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(25,2)) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) + null sort order: az + sort order: ++ + Map-reduce partition columns: _col1 (type: decimal(15,2)) + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: decimal(25,2)) + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: decimal(25,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS LAST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col2 + name: sum + window function: GenericUDAFSumHiveDecimal + window frame: RANGE PRECEDING(MAX)~CURRENT + Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: decimal(35,2)) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(sum(e011_01.c1)) over( + partition by e011_03.c2 order by e011_03.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c1, e011_03.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Input: default@e011_03 +#### A masked pattern was here #### +POSTHOOK: query: select sum(sum(e011_01.c1)) over( + partition by e011_03.c2 order by e011_03.c1) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c1, e011_03.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Input: default@e011_03 +#### A masked pattern was here #### +1.00 +3.00 +5.00 +7.00 +PREHOOK: query: explain select sum(corr(e011_01.c1, e011_03.c1)) + over(partition by e011_01.c2 order by e011_03.c2) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c2, e011_01.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Input: default@e011_03 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(corr(e011_01.c1, e011_03.c1)) + over(partition by e011_01.c2 order by e011_03.c2) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c2, e011_01.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Input: default@e011_03 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: e011_01 + filterExpr: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(15,2)) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(15,2)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: e011_03 + filterExpr: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(15,2)) + Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(15,2)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: decimal(15,2)) + 1 _col0 (type: decimal(15,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 4 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: corr(_col0, _col2) + keys: _col1 (type: decimal(15,2)), _col3 (type: decimal(15,2)) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) + null sort order: az + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(15,2)) + Statistics: Num rows: 2 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: corr(VALUE._col0) + keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)), _col2 (type: double) + outputColumnNames: _col0, _col1, _col2 + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: double + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS LAST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col2 + name: sum + window function: GenericUDAFSumDouble + window frame: RANGE PRECEDING(MAX)~CURRENT + Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(corr(e011_01.c1, e011_03.c1)) + over(partition by e011_01.c2 order by e011_03.c2) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c2, e011_01.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@e011_01 +PREHOOK: Input: default@e011_03 +#### A masked pattern was here #### +POSTHOOK: query: select sum(corr(e011_01.c1, e011_03.c1)) + over(partition by e011_01.c2 order by e011_03.c2) + from e011_01 + join e011_03 on e011_01.c1 = e011_03.c1 + group by e011_03.c2, e011_01.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@e011_01 +POSTHOOK: Input: default@e011_03 +#### A masked pattern was here #### +NULL +NULL +NULL +NULL diff --git ql/src/test/results/clientpositive/llap/parallel_join0.q.out ql/src/test/results/clientpositive/llap/parallel_join0.q.out new file mode 100644 index 0000000000..2abc85396e --- /dev/null +++ ql/src/test/results/clientpositive/llap/parallel_join0.q.out @@ -0,0 +1,251 @@ +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + sort order: ++++ + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 9 val_9 +0 val_0 9 val_9 +0 val_0 9 val_9 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 2 val_2 +2 val_2 4 val_4 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 8 val_8 +2 val_2 9 val_9 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 2 val_2 +4 val_4 4 val_4 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 8 val_8 +4 val_4 9 val_9 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 9 val_9 +5 val_5 9 val_9 +5 val_5 9 val_9 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 2 val_2 +8 val_8 4 val_4 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 8 val_8 +8 val_8 9 val_9 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 2 val_2 +9 val_9 4 val_4 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 8 val_8 +9 val_9 9 val_9 diff --git ql/src/test/results/clientpositive/parallel_join1.q.out ql/src/test/results/clientpositive/llap/parallel_join1.q.out similarity index 73% rename from ql/src/test/results/clientpositive/parallel_join1.q.out rename to ql/src/test/results/clientpositive/llap/parallel_join1.q.out index 5da5745908..4a54f24f4e 100644 --- ql/src/test/results/clientpositive/parallel_join1.q.out +++ ql/src/test/results/clientpositive/llap/parallel_join1.q.out @@ -20,86 +20,118 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_j1_n19 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + filterExpr: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src2 + filterExpr: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j1_n19 - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j1_n19 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -111,7 +143,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1_n19 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -119,30 +151,6 @@ STAGE PLANS: Column Types: int, string Table: default.dest_j1_n19 - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) INSERT OVERWRITE TABLE dest_j1_n19 SELECT src1.key, src2.value PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/parallel_orderby.q.out ql/src/test/results/clientpositive/llap/parallel_orderby.q.out similarity index 77% rename from ql/src/test/results/clientpositive/parallel_orderby.q.out rename to ql/src/test/results/clientpositive/llap/parallel_orderby.q.out index 4349a145dd..f49f8f9503 100644 --- ql/src/test/results/clientpositive/parallel_orderby.q.out +++ ql/src/test/results/clientpositive/llap/parallel_orderby.q.out @@ -36,68 +36,71 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@total_ordered STAGE DEPENDENCIES: Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-4 depends on stages: Stage-0, Stage-2 + Stage-3 depends on stages: Stage-4 Stage-0 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-0 - Stage-2 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src5_n2 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.total_ordered - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: col1, col2 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll') - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src5_n2 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: Select Operator - expressions: _col0 (type: struct), _col1 (type: struct) + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.total_ordered + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: col1, col2 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-0 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### + Stage: Stage-2 + Dependency Collection - Stage: Stage-3 + Stage: Stage-4 Create Table columns: key string, value string name: default.total_ordered @@ -105,7 +108,7 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -113,6 +116,12 @@ STAGE PLANS: Column Types: string, string Table: default.total_ordered + Stage: Stage-0 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + PREHOOK: query: create table total_ordered as select * from src5_n2 order by key, value PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src5_n2 diff --git ql/src/test/results/clientpositive/parenthesis_star_by.q.out ql/src/test/results/clientpositive/llap/parenthesis_star_by.q.out similarity index 100% rename from ql/src/test/results/clientpositive/parenthesis_star_by.q.out rename to ql/src/test/results/clientpositive/llap/parenthesis_star_by.q.out index 1924c7eb9a..4ec77f162d 100644 --- ql/src/test/results/clientpositive/parenthesis_star_by.q.out +++ ql/src/test/results/clientpositive/llap/parenthesis_star_by.q.out @@ -6,23 +6,13 @@ POSTHOOK: query: SELECT key, value FROM src CLUSTER BY key, value POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -10 val_10 100 val_100 100 val_100 -103 val_103 -103 val_103 104 val_104 104 val_104 105 val_105 -11 val_11 -111 val_111 113 val_113 113 val_113 -114 val_114 -116 val_116 118 val_118 118 val_118 119 val_119 @@ -32,19 +22,228 @@ POSTHOOK: Input: default@src 12 val_12 120 val_120 120 val_120 -125 val_125 -125 val_125 -126 val_126 128 val_128 128 val_128 128 val_128 129 val_129 129 val_129 -131 val_131 133 val_133 +136 val_136 +145 val_145 +155 val_155 +158 val_158 +160 val_160 +162 val_162 +167 val_167 +167 val_167 +167 val_167 +168 val_168 +17 val_17 +170 val_170 +174 val_174 +174 val_174 +175 val_175 +175 val_175 +178 val_178 +18 val_18 +18 val_18 +180 val_180 +181 val_181 +186 val_186 +19 val_19 +193 val_193 +193 val_193 +193 val_193 +197 val_197 +197 val_197 +199 val_199 +199 val_199 +199 val_199 +20 val_20 +200 val_200 +200 val_200 +201 val_201 +213 val_213 +213 val_213 +214 val_214 +216 val_216 +216 val_216 +218 val_218 +219 val_219 +219 val_219 +221 val_221 +221 val_221 +222 val_222 +223 val_223 +223 val_223 +224 val_224 +224 val_224 +226 val_226 +228 val_228 +233 val_233 +233 val_233 +235 val_235 +237 val_237 +237 val_237 +239 val_239 +239 val_239 +241 val_241 +244 val_244 +247 val_247 +249 val_249 +256 val_256 +256 val_256 +260 val_260 +262 val_262 +263 val_263 +273 val_273 +273 val_273 +273 val_273 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +28 val_28 +281 val_281 +281 val_281 +283 val_283 +286 val_286 +287 val_287 +288 val_288 +288 val_288 +292 val_292 +298 val_298 +298 val_298 +298 val_298 +302 val_302 +306 val_306 +308 val_308 +310 val_310 +323 val_323 +327 val_327 +327 val_327 +327 val_327 +33 val_33 +336 val_336 +341 val_341 +344 val_344 +344 val_344 +348 val_348 +348 val_348 +348 val_348 +348 val_348 +348 val_348 +351 val_351 +353 val_353 +353 val_353 +362 val_362 +366 val_366 +375 val_375 +382 val_382 +382 val_382 +384 val_384 +384 val_384 +384 val_384 +393 val_393 +395 val_395 +395 val_395 +396 val_396 +396 val_396 +396 val_396 +397 val_397 +397 val_397 +399 val_399 +399 val_399 +401 val_401 +401 val_401 +401 val_401 +401 val_401 +401 val_401 +403 val_403 +403 val_403 +403 val_403 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +409 val_409 +409 val_409 +409 val_409 +411 val_411 +418 val_418 +419 val_419 +427 val_427 +43 val_43 +432 val_432 +435 val_435 +436 val_436 +439 val_439 +439 val_439 +443 val_443 +453 val_453 +455 val_455 +459 val_459 +459 val_459 +460 val_460 +462 val_462 +462 val_462 +47 val_47 +472 val_472 +477 val_477 +478 val_478 +478 val_478 +479 val_479 +482 val_482 +485 val_485 +493 val_493 +494 val_494 +495 val_495 +496 val_496 +497 val_497 +5 val_5 +5 val_5 +5 val_5 +54 val_54 +58 val_58 +58 val_58 +64 val_64 +67 val_67 +67 val_67 +70 val_70 +70 val_70 +70 val_70 +77 val_77 +8 val_8 +80 val_80 +83 val_83 +83 val_83 +84 val_84 +84 val_84 +85 val_85 +86 val_86 +90 val_90 +90 val_90 +90 val_90 +97 val_97 +97 val_97 +98 val_98 +98 val_98 +0 val_0 +0 val_0 +0 val_0 +10 val_10 +103 val_103 +103 val_103 +11 val_11 +111 val_111 +114 val_114 +116 val_116 +125 val_125 +125 val_125 +126 val_126 +131 val_131 134 val_134 134 val_134 -136 val_136 137 val_137 137 val_137 138 val_138 @@ -52,7 +251,6 @@ POSTHOOK: Input: default@src 138 val_138 138 val_138 143 val_143 -145 val_145 146 val_146 146 val_146 149 val_149 @@ -63,72 +261,39 @@ POSTHOOK: Input: default@src 152 val_152 152 val_152 153 val_153 -155 val_155 156 val_156 157 val_157 -158 val_158 -160 val_160 -162 val_162 163 val_163 164 val_164 164 val_164 165 val_165 165 val_165 166 val_166 -167 val_167 -167 val_167 -167 val_167 -168 val_168 169 val_169 169 val_169 169 val_169 169 val_169 -17 val_17 -170 val_170 172 val_172 172 val_172 -174 val_174 -174 val_174 -175 val_175 -175 val_175 176 val_176 176 val_176 177 val_177 -178 val_178 179 val_179 179 val_179 -18 val_18 -18 val_18 -180 val_180 -181 val_181 183 val_183 -186 val_186 187 val_187 187 val_187 187 val_187 189 val_189 -19 val_19 190 val_190 191 val_191 191 val_191 192 val_192 -193 val_193 -193 val_193 -193 val_193 194 val_194 195 val_195 195 val_195 196 val_196 -197 val_197 -197 val_197 -199 val_199 -199 val_199 -199 val_199 2 val_2 -20 val_20 -200 val_200 -200 val_200 -201 val_201 202 val_202 203 val_203 203 val_203 @@ -141,25 +306,8 @@ POSTHOOK: Input: default@src 208 val_208 209 val_209 209 val_209 -213 val_213 -213 val_213 -214 val_214 -216 val_216 -216 val_216 217 val_217 217 val_217 -218 val_218 -219 val_219 -219 val_219 -221 val_221 -221 val_221 -222 val_222 -223 val_223 -223 val_223 -224 val_224 -224 val_224 -226 val_226 -228 val_228 229 val_229 229 val_229 230 val_230 @@ -167,84 +315,45 @@ POSTHOOK: Input: default@src 230 val_230 230 val_230 230 val_230 -233 val_233 -233 val_233 -235 val_235 -237 val_237 -237 val_237 238 val_238 238 val_238 -239 val_239 -239 val_239 24 val_24 24 val_24 -241 val_241 242 val_242 242 val_242 -244 val_244 -247 val_247 248 val_248 -249 val_249 252 val_252 255 val_255 255 val_255 -256 val_256 -256 val_256 257 val_257 258 val_258 26 val_26 26 val_26 -260 val_260 -262 val_262 -263 val_263 265 val_265 265 val_265 266 val_266 27 val_27 272 val_272 272 val_272 -273 val_273 -273 val_273 -273 val_273 274 val_274 275 val_275 -277 val_277 -277 val_277 -277 val_277 -277 val_277 278 val_278 278 val_278 -28 val_28 280 val_280 280 val_280 -281 val_281 -281 val_281 282 val_282 282 val_282 -283 val_283 284 val_284 285 val_285 -286 val_286 -287 val_287 -288 val_288 -288 val_288 289 val_289 291 val_291 -292 val_292 296 val_296 -298 val_298 -298 val_298 -298 val_298 30 val_30 -302 val_302 305 val_305 -306 val_306 307 val_307 307 val_307 -308 val_308 309 val_309 309 val_309 -310 val_310 311 val_311 311 val_311 311 val_311 @@ -261,46 +370,27 @@ POSTHOOK: Input: default@src 321 val_321 322 val_322 322 val_322 -323 val_323 325 val_325 325 val_325 -327 val_327 -327 val_327 -327 val_327 -33 val_33 331 val_331 331 val_331 332 val_332 333 val_333 333 val_333 335 val_335 -336 val_336 338 val_338 339 val_339 34 val_34 -341 val_341 342 val_342 342 val_342 -344 val_344 -344 val_344 345 val_345 -348 val_348 -348 val_348 -348 val_348 -348 val_348 -348 val_348 35 val_35 35 val_35 35 val_35 -351 val_351 -353 val_353 -353 val_353 356 val_356 360 val_360 -362 val_362 364 val_364 365 val_365 -366 val_366 367 val_367 367 val_367 368 val_368 @@ -311,52 +401,20 @@ POSTHOOK: Input: default@src 37 val_37 373 val_373 374 val_374 -375 val_375 377 val_377 378 val_378 379 val_379 -382 val_382 -382 val_382 -384 val_384 -384 val_384 -384 val_384 386 val_386 389 val_389 392 val_392 -393 val_393 394 val_394 -395 val_395 -395 val_395 -396 val_396 -396 val_396 -396 val_396 -397 val_397 -397 val_397 -399 val_399 -399 val_399 4 val_4 400 val_400 -401 val_401 -401 val_401 -401 val_401 -401 val_401 -401 val_401 402 val_402 -403 val_403 -403 val_403 -403 val_403 404 val_404 404 val_404 -406 val_406 -406 val_406 -406 val_406 -406 val_406 407 val_407 -409 val_409 -409 val_409 -409 val_409 41 val_41 -411 val_411 413 val_413 413 val_413 414 val_414 @@ -364,52 +422,35 @@ POSTHOOK: Input: default@src 417 val_417 417 val_417 417 val_417 -418 val_418 -419 val_419 42 val_42 42 val_42 421 val_421 424 val_424 424 val_424 -427 val_427 429 val_429 429 val_429 -43 val_43 430 val_430 430 val_430 430 val_430 431 val_431 431 val_431 431 val_431 -432 val_432 -435 val_435 -436 val_436 437 val_437 438 val_438 438 val_438 438 val_438 -439 val_439 -439 val_439 44 val_44 -443 val_443 444 val_444 446 val_446 448 val_448 449 val_449 452 val_452 -453 val_453 454 val_454 454 val_454 454 val_454 -455 val_455 457 val_457 458 val_458 458 val_458 -459 val_459 -459 val_459 -460 val_460 -462 val_462 -462 val_462 463 val_463 463 val_463 466 val_466 @@ -425,22 +466,14 @@ POSTHOOK: Input: default@src 469 val_469 469 val_469 469 val_469 -47 val_47 470 val_470 -472 val_472 475 val_475 -477 val_477 -478 val_478 -478 val_478 -479 val_479 480 val_480 480 val_480 480 val_480 481 val_481 -482 val_482 483 val_483 484 val_484 -485 val_485 487 val_487 489 val_489 489 val_489 @@ -450,62 +483,29 @@ POSTHOOK: Input: default@src 491 val_491 492 val_492 492 val_492 -493 val_493 -494 val_494 -495 val_495 -496 val_496 -497 val_497 498 val_498 498 val_498 498 val_498 -5 val_5 -5 val_5 -5 val_5 51 val_51 51 val_51 53 val_53 -54 val_54 57 val_57 -58 val_58 -58 val_58 -64 val_64 65 val_65 66 val_66 -67 val_67 -67 val_67 69 val_69 -70 val_70 -70 val_70 -70 val_70 72 val_72 72 val_72 74 val_74 76 val_76 76 val_76 -77 val_77 78 val_78 -8 val_8 -80 val_80 82 val_82 -83 val_83 -83 val_83 -84 val_84 -84 val_84 -85 val_85 -86 val_86 -87 val_87 -9 val_9 -90 val_90 -90 val_90 -90 val_90 +87 val_87 +9 val_9 92 val_92 95 val_95 95 val_95 96 val_96 -97 val_97 -97 val_97 -98 val_98 -98 val_98 PREHOOK: query: SELECT key, value FROM src ORDER BY key ASC, value ASC PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -1979,104 +1979,303 @@ POSTHOOK: Input: default@src 495 val_495 496 val_496 497 val_497 -498 val_498 -498 val_498 -498 val_498 +498 val_498 +498 val_498 +498 val_498 +5 val_5 +5 val_5 +5 val_5 +51 val_51 +51 val_51 +53 val_53 +54 val_54 +57 val_57 +58 val_58 +58 val_58 +64 val_64 +65 val_65 +66 val_66 +67 val_67 +67 val_67 +69 val_69 +70 val_70 +70 val_70 +70 val_70 +72 val_72 +72 val_72 +74 val_74 +76 val_76 +76 val_76 +77 val_77 +78 val_78 +8 val_8 +80 val_80 +82 val_82 +83 val_83 +83 val_83 +84 val_84 +84 val_84 +85 val_85 +86 val_86 +87 val_87 +9 val_9 +90 val_90 +90 val_90 +90 val_90 +92 val_92 +95 val_95 +95 val_95 +96 val_96 +97 val_97 +97 val_97 +98 val_98 +98 val_98 +PREHOOK: query: SELECT key, value FROM src CLUSTER BY (key, value) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT key, value FROM src CLUSTER BY (key, value) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +100 val_100 +100 val_100 +104 val_104 +104 val_104 +105 val_105 +113 val_113 +113 val_113 +118 val_118 +118 val_118 +119 val_119 +119 val_119 +119 val_119 +12 val_12 +12 val_12 +120 val_120 +120 val_120 +128 val_128 +128 val_128 +128 val_128 +129 val_129 +129 val_129 +133 val_133 +136 val_136 +145 val_145 +155 val_155 +158 val_158 +160 val_160 +162 val_162 +167 val_167 +167 val_167 +167 val_167 +168 val_168 +17 val_17 +170 val_170 +174 val_174 +174 val_174 +175 val_175 +175 val_175 +178 val_178 +18 val_18 +18 val_18 +180 val_180 +181 val_181 +186 val_186 +19 val_19 +193 val_193 +193 val_193 +193 val_193 +197 val_197 +197 val_197 +199 val_199 +199 val_199 +199 val_199 +20 val_20 +200 val_200 +200 val_200 +201 val_201 +213 val_213 +213 val_213 +214 val_214 +216 val_216 +216 val_216 +218 val_218 +219 val_219 +219 val_219 +221 val_221 +221 val_221 +222 val_222 +223 val_223 +223 val_223 +224 val_224 +224 val_224 +226 val_226 +228 val_228 +233 val_233 +233 val_233 +235 val_235 +237 val_237 +237 val_237 +239 val_239 +239 val_239 +241 val_241 +244 val_244 +247 val_247 +249 val_249 +256 val_256 +256 val_256 +260 val_260 +262 val_262 +263 val_263 +273 val_273 +273 val_273 +273 val_273 +277 val_277 +277 val_277 +277 val_277 +277 val_277 +28 val_28 +281 val_281 +281 val_281 +283 val_283 +286 val_286 +287 val_287 +288 val_288 +288 val_288 +292 val_292 +298 val_298 +298 val_298 +298 val_298 +302 val_302 +306 val_306 +308 val_308 +310 val_310 +323 val_323 +327 val_327 +327 val_327 +327 val_327 +33 val_33 +336 val_336 +341 val_341 +344 val_344 +344 val_344 +348 val_348 +348 val_348 +348 val_348 +348 val_348 +348 val_348 +351 val_351 +353 val_353 +353 val_353 +362 val_362 +366 val_366 +375 val_375 +382 val_382 +382 val_382 +384 val_384 +384 val_384 +384 val_384 +393 val_393 +395 val_395 +395 val_395 +396 val_396 +396 val_396 +396 val_396 +397 val_397 +397 val_397 +399 val_399 +399 val_399 +401 val_401 +401 val_401 +401 val_401 +401 val_401 +401 val_401 +403 val_403 +403 val_403 +403 val_403 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +409 val_409 +409 val_409 +409 val_409 +411 val_411 +418 val_418 +419 val_419 +427 val_427 +43 val_43 +432 val_432 +435 val_435 +436 val_436 +439 val_439 +439 val_439 +443 val_443 +453 val_453 +455 val_455 +459 val_459 +459 val_459 +460 val_460 +462 val_462 +462 val_462 +47 val_47 +472 val_472 +477 val_477 +478 val_478 +478 val_478 +479 val_479 +482 val_482 +485 val_485 +493 val_493 +494 val_494 +495 val_495 +496 val_496 +497 val_497 5 val_5 5 val_5 5 val_5 -51 val_51 -51 val_51 -53 val_53 54 val_54 -57 val_57 58 val_58 58 val_58 64 val_64 -65 val_65 -66 val_66 67 val_67 67 val_67 -69 val_69 70 val_70 70 val_70 70 val_70 -72 val_72 -72 val_72 -74 val_74 -76 val_76 -76 val_76 77 val_77 -78 val_78 8 val_8 80 val_80 -82 val_82 83 val_83 83 val_83 84 val_84 84 val_84 85 val_85 86 val_86 -87 val_87 -9 val_9 90 val_90 90 val_90 90 val_90 -92 val_92 -95 val_95 -95 val_95 -96 val_96 97 val_97 97 val_97 98 val_98 98 val_98 -PREHOOK: query: SELECT key, value FROM src CLUSTER BY (key, value) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT key, value FROM src CLUSTER BY (key, value) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### 0 val_0 0 val_0 0 val_0 10 val_10 -100 val_100 -100 val_100 103 val_103 103 val_103 -104 val_104 -104 val_104 -105 val_105 11 val_11 111 val_111 -113 val_113 -113 val_113 114 val_114 116 val_116 -118 val_118 -118 val_118 -119 val_119 -119 val_119 -119 val_119 -12 val_12 -12 val_12 -120 val_120 -120 val_120 125 val_125 125 val_125 126 val_126 -128 val_128 -128 val_128 -128 val_128 -129 val_129 -129 val_129 131 val_131 -133 val_133 134 val_134 134 val_134 -136 val_136 137 val_137 137 val_137 138 val_138 @@ -2084,7 +2283,6 @@ POSTHOOK: Input: default@src 138 val_138 138 val_138 143 val_143 -145 val_145 146 val_146 146 val_146 149 val_149 @@ -2095,72 +2293,39 @@ POSTHOOK: Input: default@src 152 val_152 152 val_152 153 val_153 -155 val_155 156 val_156 157 val_157 -158 val_158 -160 val_160 -162 val_162 163 val_163 164 val_164 164 val_164 165 val_165 165 val_165 166 val_166 -167 val_167 -167 val_167 -167 val_167 -168 val_168 169 val_169 169 val_169 169 val_169 169 val_169 -17 val_17 -170 val_170 172 val_172 172 val_172 -174 val_174 -174 val_174 -175 val_175 -175 val_175 176 val_176 176 val_176 177 val_177 -178 val_178 179 val_179 179 val_179 -18 val_18 -18 val_18 -180 val_180 -181 val_181 183 val_183 -186 val_186 187 val_187 187 val_187 187 val_187 189 val_189 -19 val_19 190 val_190 191 val_191 191 val_191 192 val_192 -193 val_193 -193 val_193 -193 val_193 194 val_194 195 val_195 195 val_195 196 val_196 -197 val_197 -197 val_197 -199 val_199 -199 val_199 -199 val_199 2 val_2 -20 val_20 -200 val_200 -200 val_200 -201 val_201 202 val_202 203 val_203 203 val_203 @@ -2173,25 +2338,8 @@ POSTHOOK: Input: default@src 208 val_208 209 val_209 209 val_209 -213 val_213 -213 val_213 -214 val_214 -216 val_216 -216 val_216 217 val_217 217 val_217 -218 val_218 -219 val_219 -219 val_219 -221 val_221 -221 val_221 -222 val_222 -223 val_223 -223 val_223 -224 val_224 -224 val_224 -226 val_226 -228 val_228 229 val_229 229 val_229 230 val_230 @@ -2199,84 +2347,45 @@ POSTHOOK: Input: default@src 230 val_230 230 val_230 230 val_230 -233 val_233 -233 val_233 -235 val_235 -237 val_237 -237 val_237 238 val_238 238 val_238 -239 val_239 -239 val_239 24 val_24 24 val_24 -241 val_241 242 val_242 242 val_242 -244 val_244 -247 val_247 248 val_248 -249 val_249 252 val_252 255 val_255 255 val_255 -256 val_256 -256 val_256 257 val_257 258 val_258 26 val_26 26 val_26 -260 val_260 -262 val_262 -263 val_263 265 val_265 265 val_265 266 val_266 27 val_27 272 val_272 272 val_272 -273 val_273 -273 val_273 -273 val_273 274 val_274 275 val_275 -277 val_277 -277 val_277 -277 val_277 -277 val_277 278 val_278 278 val_278 -28 val_28 280 val_280 280 val_280 -281 val_281 -281 val_281 282 val_282 282 val_282 -283 val_283 284 val_284 285 val_285 -286 val_286 -287 val_287 -288 val_288 -288 val_288 289 val_289 291 val_291 -292 val_292 296 val_296 -298 val_298 -298 val_298 -298 val_298 30 val_30 -302 val_302 305 val_305 -306 val_306 307 val_307 307 val_307 -308 val_308 309 val_309 309 val_309 -310 val_310 311 val_311 311 val_311 311 val_311 @@ -2293,46 +2402,27 @@ POSTHOOK: Input: default@src 321 val_321 322 val_322 322 val_322 -323 val_323 325 val_325 325 val_325 -327 val_327 -327 val_327 -327 val_327 -33 val_33 331 val_331 331 val_331 332 val_332 333 val_333 333 val_333 335 val_335 -336 val_336 338 val_338 339 val_339 34 val_34 -341 val_341 342 val_342 342 val_342 -344 val_344 -344 val_344 345 val_345 -348 val_348 -348 val_348 -348 val_348 -348 val_348 -348 val_348 35 val_35 35 val_35 35 val_35 -351 val_351 -353 val_353 -353 val_353 356 val_356 360 val_360 -362 val_362 364 val_364 365 val_365 -366 val_366 367 val_367 367 val_367 368 val_368 @@ -2343,52 +2433,20 @@ POSTHOOK: Input: default@src 37 val_37 373 val_373 374 val_374 -375 val_375 377 val_377 378 val_378 379 val_379 -382 val_382 -382 val_382 -384 val_384 -384 val_384 -384 val_384 386 val_386 389 val_389 392 val_392 -393 val_393 394 val_394 -395 val_395 -395 val_395 -396 val_396 -396 val_396 -396 val_396 -397 val_397 -397 val_397 -399 val_399 -399 val_399 4 val_4 400 val_400 -401 val_401 -401 val_401 -401 val_401 -401 val_401 -401 val_401 402 val_402 -403 val_403 -403 val_403 -403 val_403 404 val_404 404 val_404 -406 val_406 -406 val_406 -406 val_406 -406 val_406 407 val_407 -409 val_409 -409 val_409 -409 val_409 41 val_41 -411 val_411 413 val_413 413 val_413 414 val_414 @@ -2396,52 +2454,35 @@ POSTHOOK: Input: default@src 417 val_417 417 val_417 417 val_417 -418 val_418 -419 val_419 42 val_42 42 val_42 421 val_421 424 val_424 424 val_424 -427 val_427 429 val_429 429 val_429 -43 val_43 430 val_430 430 val_430 430 val_430 431 val_431 431 val_431 431 val_431 -432 val_432 -435 val_435 -436 val_436 437 val_437 438 val_438 438 val_438 438 val_438 -439 val_439 -439 val_439 44 val_44 -443 val_443 444 val_444 446 val_446 448 val_448 449 val_449 452 val_452 -453 val_453 454 val_454 454 val_454 454 val_454 -455 val_455 457 val_457 458 val_458 458 val_458 -459 val_459 -459 val_459 -460 val_460 -462 val_462 -462 val_462 463 val_463 463 val_463 466 val_466 @@ -2457,22 +2498,14 @@ POSTHOOK: Input: default@src 469 val_469 469 val_469 469 val_469 -47 val_47 470 val_470 -472 val_472 475 val_475 -477 val_477 -478 val_478 -478 val_478 -479 val_479 480 val_480 480 val_480 480 val_480 481 val_481 -482 val_482 483 val_483 484 val_484 -485 val_485 487 val_487 489 val_489 489 val_489 @@ -2482,62 +2515,29 @@ POSTHOOK: Input: default@src 491 val_491 492 val_492 492 val_492 -493 val_493 -494 val_494 -495 val_495 -496 val_496 -497 val_497 498 val_498 498 val_498 498 val_498 -5 val_5 -5 val_5 -5 val_5 51 val_51 51 val_51 53 val_53 -54 val_54 57 val_57 -58 val_58 -58 val_58 -64 val_64 65 val_65 66 val_66 -67 val_67 -67 val_67 69 val_69 -70 val_70 -70 val_70 -70 val_70 72 val_72 72 val_72 74 val_74 76 val_76 76 val_76 -77 val_77 78 val_78 -8 val_8 -80 val_80 82 val_82 -83 val_83 -83 val_83 -84 val_84 -84 val_84 -85 val_85 -86 val_86 87 val_87 9 val_9 -90 val_90 -90 val_90 -90 val_90 92 val_92 95 val_95 95 val_95 96 val_96 -97 val_97 -97 val_97 -98 val_98 -98 val_98 PREHOOK: query: SELECT key, value FROM src ORDER BY key ASC, value ASC PREHOOK: type: QUERY PREHOOK: Input: default@src diff --git ql/src/test/results/clientpositive/parquet_create.q.out ql/src/test/results/clientpositive/llap/parquet_create.q.out similarity index 100% rename from ql/src/test/results/clientpositive/parquet_create.q.out rename to ql/src/test/results/clientpositive/llap/parquet_create.q.out index a37309e24b..0d2bfec8a5 100644 --- ql/src/test/results/clientpositive/parquet_create.q.out +++ ql/src/test/results/clientpositive/llap/parquet_create.q.out @@ -130,9 +130,9 @@ POSTHOOK: query: SELECT id, count(0) FROM parquet_create group by id POSTHOOK: type: QUERY POSTHOOK: Input: default@parquet_create #### A masked pattern was here #### +3 1 1 1 2 1 -3 1 PREHOOK: query: SELECT str from parquet_create PREHOOK: type: QUERY PREHOOK: Input: default@parquet_create diff --git ql/src/test/results/clientpositive/parquet_int64_timestamp_int96_compatibility.q.out ql/src/test/results/clientpositive/llap/parquet_int64_timestamp_int96_compatibility.q.out similarity index 98% rename from ql/src/test/results/clientpositive/parquet_int64_timestamp_int96_compatibility.q.out rename to ql/src/test/results/clientpositive/llap/parquet_int64_timestamp_int96_compatibility.q.out index 72fc69a1c8..dd9582db05 100644 --- ql/src/test/results/clientpositive/parquet_int64_timestamp_int96_compatibility.q.out +++ ql/src/test/results/clientpositive/llap/parquet_int64_timestamp_int96_compatibility.q.out @@ -157,9 +157,9 @@ POSTHOOK: query: select * from parquet_mixed_timestamp where ts < cast ('1900-12 POSTHOOK: type: QUERY POSTHOOK: Input: default@parquet_mixed_timestamp #### A masked pattern was here #### -0 0001-01-01 00:00:00 +0 0001-01-03 00:00:00 1 1677-09-21 00:12:43.145224 -10 0001-01-01 00:00:00 +10 0001-01-03 00:00:00 11 1677-09-21 00:12:43.145224192 PREHOOK: query: select count(*) from parquet_mixed_timestamp where ts = cast ('1970-01-01 00:00:00.00' as timestamp) PREHOOK: type: QUERY @@ -188,14 +188,11 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@parquet_int64 POSTHOOK: Input: default@parquet_mixed_timestamp #### A masked pattern was here #### -0 0001-01-01 00:00:00 0 0001-01-01 00:00:00 1 1677-09-21 00:12:43.145224 1 1677-09-21 00:12:43.145224 -2 1969-12-31 23:59:59.999999 2 1969-12-31 23:59:59.999999 3 1970-01-01 00:00:00 3 1970-01-01 00:00:00 4 2013-09-27 01:36:18 4 2013-09-27 01:36:18 5 2018-01-02 13:14:15.678999 5 2018-01-02 13:14:15.678999 6 2262-04-11 23:47:16.854775 6 2262-04-11 23:47:16.854775 7 9999-12-31 23:59:59.999999 7 9999-12-31 23:59:59.999999 -10 0001-01-01 00:00:00 0 0001-01-01 00:00:00 13 1970-01-01 00:00:00 3 1970-01-01 00:00:00 15 2018-01-02 13:14:15.678999 5 2018-01-02 13:14:15.678999 diff --git ql/src/test/results/clientpositive/parquet_join.q.out ql/src/test/results/clientpositive/llap/parquet_join.q.out similarity index 52% rename from ql/src/test/results/clientpositive/parquet_join.q.out rename to ql/src/test/results/clientpositive/llap/parquet_join.q.out index f150f846e1..9525ebb8cd 100644 --- ql/src/test/results/clientpositive/parquet_join.q.out +++ ql/src/test/results/clientpositive/llap/parquet_join.q.out @@ -77,63 +77,77 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: p1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: p1 + filterExpr: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: p2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), myvalue (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 3 + Map Operator Tree: + TableScan + alias: p2 + filterExpr: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), myvalue (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: all inputs (cache only) + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -164,70 +178,74 @@ POSTHOOK: Input: default@parquet_jointable1 POSTHOOK: Input: default@parquet_jointable2 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-3 depends on stages: Stage-4 - Stage-0 depends on stages: Stage-3 + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-4 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:p1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:p1 - TableScan - alias: p1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: p2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), myvalue (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 2 <- Map 1 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: p1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 2 + Map Operator Tree: + TableScan + alias: p2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), myvalue (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 0 Map 1 + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) Stage: Stage-0 Fetch Operator @@ -300,38 +318,70 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: p2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Map 2 <- Map 1 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: p1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: all inputs (cache only) + Map 2 + Map Operator Tree: + TableScan + alias: p2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + input vertices: + 0 Map 1 + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 388 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: all inputs (cache only) Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_mixed_partition_formats2.q.out ql/src/test/results/clientpositive/llap/parquet_mixed_partition_formats2.q.out similarity index 88% rename from ql/src/test/results/clientpositive/parquet_mixed_partition_formats2.q.out rename to ql/src/test/results/clientpositive/llap/parquet_mixed_partition_formats2.q.out index 575e83fa11..d32d782fc8 100644 --- ql/src/test/results/clientpositive/parquet_mixed_partition_formats2.q.out +++ ql/src/test/results/clientpositive/llap/parquet_mixed_partition_formats2.q.out @@ -37,12 +37,12 @@ POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@parquet_table_json_partition POSTHOOK: Output: default@parquet_table_json_partition@ts=20150101 -PREHOOK: query: SELECT * FROM parquet_table_json_partition LIMIT 100 +PREHOOK: query: SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100 PREHOOK: type: QUERY PREHOOK: Input: default@parquet_table_json_partition PREHOOK: Input: default@parquet_table_json_partition@ts=20150101 #### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM parquet_table_json_partition LIMIT 100 +POSTHOOK: query: SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100 POSTHOOK: type: QUERY POSTHOOK: Input: default@parquet_table_json_partition POSTHOOK: Input: default@parquet_table_json_partition@ts=20150101 @@ -63,25 +63,25 @@ POSTHOOK: query: ALTER TABLE parquet_table_json_partition POSTHOOK: type: ALTERTABLE_FILEFORMAT POSTHOOK: Input: default@parquet_table_json_partition POSTHOOK: Output: default@parquet_table_json_partition -PREHOOK: query: SELECT * FROM parquet_table_json_partition LIMIT 100 +PREHOOK: query: SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100 PREHOOK: type: QUERY PREHOOK: Input: default@parquet_table_json_partition PREHOOK: Input: default@parquet_table_json_partition@ts=20150101 #### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM parquet_table_json_partition LIMIT 100 +POSTHOOK: query: SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100 POSTHOOK: type: QUERY POSTHOOK: Input: default@parquet_table_json_partition POSTHOOK: Input: default@parquet_table_json_partition@ts=20150101 #### A masked pattern was here #### 1 {"country":1,"state":1} [2,3] 20150101 2 {"country":1,"state":2} [] 20150101 -PREHOOK: query: CREATE TABLE new_table AS SELECT * FROM parquet_table_json_partition LIMIT 100 +PREHOOK: query: CREATE TABLE new_table AS SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@parquet_table_json_partition PREHOOK: Input: default@parquet_table_json_partition@ts=20150101 PREHOOK: Output: database:default PREHOOK: Output: default@new_table -POSTHOOK: query: CREATE TABLE new_table AS SELECT * FROM parquet_table_json_partition LIMIT 100 +POSTHOOK: query: CREATE TABLE new_table AS SELECT * FROM parquet_table_json_partition ORDER BY address, reports LIMIT 100 POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@parquet_table_json_partition POSTHOOK: Input: default@parquet_table_json_partition@ts=20150101 @@ -91,13 +91,13 @@ POSTHOOK: Lineage: new_table.address SIMPLE [(parquet_table_json_partition)parqu POSTHOOK: Lineage: new_table.id SIMPLE [(parquet_table_json_partition)parquet_table_json_partition.FieldSchema(name:id, type:bigint, comment:from deserializer), ] POSTHOOK: Lineage: new_table.reports SIMPLE [(parquet_table_json_partition)parquet_table_json_partition.FieldSchema(name:reports, type:array, comment:from deserializer), ] POSTHOOK: Lineage: new_table.ts SIMPLE [(parquet_table_json_partition)parquet_table_json_partition.FieldSchema(name:ts, type:string, comment:null), ] -PREHOOK: query: SELECT * FROM new_table +PREHOOK: query: SELECT * FROM new_table ORDER BY address, reports PREHOOK: type: QUERY PREHOOK: Input: default@new_table #### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM new_table +POSTHOOK: query: SELECT * FROM new_table ORDER BY address, reports POSTHOOK: type: QUERY POSTHOOK: Input: default@new_table #### A masked pattern was here #### -2 {"country":1,"state":2} [] 20150101 1 {"country":1,"state":1} [2,3] 20150101 +2 {"country":1,"state":2} [] 20150101 diff --git ql/src/test/results/clientpositive/llap/parquet_no_row_serde.q.out ql/src/test/results/clientpositive/llap/parquet_no_row_serde.q.out new file mode 100644 index 0000000000..2e1bd207ad --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_no_row_serde.q.out @@ -0,0 +1,240 @@ +PREHOOK: query: drop table tbl_rc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table tbl_rc +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table tbl_parquet +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table tbl_parquet +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table tbl_rc (val decimal(10,0)) +row format serde 'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe' stored as rcfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl_rc +POSTHOOK: query: create table tbl_rc (val decimal(10,0)) +row format serde 'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe' stored as rcfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl_rc +PREHOOK: query: create table tbl_parquet (val decimal(10,0)) +STORED AS PARQUET +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl_parquet +POSTHOOK: query: create table tbl_parquet (val decimal(10,0)) +STORED AS PARQUET +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl_parquet +PREHOOK: query: insert into table tbl_rc values(101) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@tbl_rc +POSTHOOK: query: insert into table tbl_rc values(101) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@tbl_rc +POSTHOOK: Lineage: tbl_rc.val SCRIPT [] +PREHOOK: query: insert into table tbl_parquet values(101) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@tbl_parquet +POSTHOOK: query: insert into table tbl_parquet values(101) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@tbl_parquet +POSTHOOK: Lineage: tbl_parquet.val SCRIPT [] +PREHOOK: query: explain vectorization expression +select val, round(val, -1) from tbl_rc order by val +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_rc +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization expression +select val, round(val, -1) from tbl_rc order by val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_rc +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl_rc + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Select Operator + expressions: val (type: decimal(10,0)), round(val, -1) (type: decimal(11,0)) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 2] + selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(10,0), decimalPlaces -1) -> 2:decimal(11,0) + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(10,0)) + null sort order: z + sort order: + + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(11,0)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.row.serde.deserialize IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.RCFileInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1] + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain vectorization expression +select val, round(val, -1) from tbl_parquet order by val +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_parquet +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization expression +select val, round(val, -1) from tbl_parquet order by val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_parquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tbl_parquet + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: val (type: decimal(10,0)), round(val, -1) (type: decimal(11,0)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: decimal(10,0)) + null sort order: z + sort order: + + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: decimal(11,0)) + Execution mode: llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: false + enabledConditionsNotMet: Row deserialization of vectorized input format not supported IS false, hive.vectorized.use.vectorized.input.format IS false + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1] + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: drop table tbl_rc +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@tbl_rc +PREHOOK: Output: default@tbl_rc +POSTHOOK: query: drop table tbl_rc +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@tbl_rc +POSTHOOK: Output: default@tbl_rc +PREHOOK: query: drop table tbl_parquet +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@tbl_parquet +PREHOOK: Output: default@tbl_parquet +POSTHOOK: query: drop table tbl_parquet +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@tbl_parquet +POSTHOOK: Output: default@tbl_parquet diff --git ql/src/test/results/clientpositive/parquet_ppd_boolean.q.out ql/src/test/results/clientpositive/llap/parquet_ppd_boolean.q.out similarity index 84% rename from ql/src/test/results/clientpositive/parquet_ppd_boolean.q.out rename to ql/src/test/results/clientpositive/llap/parquet_ppd_boolean.q.out index 6e62ee49c4..79658820c0 100644 --- ql/src/test/results/clientpositive/parquet_ppd_boolean.q.out +++ ql/src/test/results/clientpositive/llap/parquet_ppd_boolean.q.out @@ -31,6 +31,11 @@ apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true PREHOOK: query: select * from newtypestbl where b!=true PREHOOK: type: QUERY PREHOOK: Input: default@newtypestbl @@ -39,11 +44,6 @@ POSTHOOK: query: select * from newtypestbl where b!=true POSTHOOK: type: QUERY POSTHOOK: Input: default@newtypestbl #### A masked pattern was here #### -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false PREHOOK: query: select * from newtypestbl where btrue PREHOOK: type: QUERY PREHOOK: Input: default@newtypestbl @@ -78,11 +73,11 @@ apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true PREHOOK: query: select * from newtypestbl where b=false PREHOOK: type: QUERY PREHOOK: Input: default@newtypestbl @@ -91,11 +86,6 @@ POSTHOOK: query: select * from newtypestbl where b=false POSTHOOK: type: QUERY POSTHOOK: Input: default@newtypestbl #### A masked pattern was here #### -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false PREHOOK: query: select * from newtypestbl where b!=false PREHOOK: type: QUERY PREHOOK: Input: default@newtypestbl @@ -109,6 +99,11 @@ apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true PREHOOK: query: select * from newtypestbl where btrue PREHOOK: type: QUERY PREHOOK: Input: default@newtypestbl @@ -203,11 +193,11 @@ apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true PREHOOK: query: select * from newtypestbl where b=false PREHOOK: type: QUERY PREHOOK: Input: default@newtypestbl @@ -216,11 +206,6 @@ POSTHOOK: query: select * from newtypestbl where b=false POSTHOOK: type: QUERY POSTHOOK: Input: default@newtypestbl #### A masked pattern was here #### -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false -hello world 11.220 false PREHOOK: query: select * from newtypestbl where b!=false PREHOOK: type: QUERY PREHOOK: Input: default@newtypestbl @@ -234,6 +219,11 @@ apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true +apple bee 0.220 true PREHOOK: query: select * from newtypestbl where b bigint + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Group By Operator - aggregations: sum(ctinyint) + aggregations: sum(VALUE._col0) Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0:tinyint) -> bigint + aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint className: VectorGroupByOperator - groupByMode: HASH + groupByMode: MERGEPARTIAL native: false - vectorProcessingMode: HASH + vectorProcessingMode: GLOBAL projectedOutputColumnNums: [0] - minReductionHashAggr: 0.99 - mode: hash + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -200,57 +220,68 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Group By Operator - aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) - minReductionHashAggr: 0.99 - mode: hash + aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToDouble(_col0) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: (UDFToDouble(_col0) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -364,71 +395,91 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Select Operator - expressions: cbigint (type: bigint) - outputColumnNames: cbigint - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [3] - Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Select Operator + expressions: cbigint (type: bigint) + outputColumnNames: cbigint + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [3] + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(cbigint) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 3:bigint) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Group By Operator - aggregations: sum(cbigint) + aggregations: sum(VALUE._col0) Group By Vectorization: - aggregators: VectorUDAFSumLong(col 3:bigint) -> bigint + aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint className: VectorGroupByOperator - groupByMode: HASH + groupByMode: MERGEPARTIAL native: false - vectorProcessingMode: HASH + vectorProcessingMode: GLOBAL projectedOutputColumnNums: [0] - minReductionHashAggr: 0.99 - mode: hash + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -489,57 +540,68 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cbigint (type: bigint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Group By Operator - aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) - minReductionHashAggr: 0.99 - mode: hash + aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToDouble(_col0) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: (UDFToDouble(_col0) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -653,71 +715,91 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Select Operator - expressions: cfloat (type: float) - outputColumnNames: cfloat - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [4] - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Select Operator + expressions: cfloat (type: float) + outputColumnNames: cfloat + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [4] + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(cfloat) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 4:float) -> double + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Group By Operator - aggregations: sum(cfloat) + aggregations: sum(VALUE._col0) Group By Vectorization: - aggregators: VectorUDAFSumDouble(col 4:float) -> double + aggregators: VectorUDAFSumDouble(col 0:double) -> double className: VectorGroupByOperator - groupByMode: HASH + groupByMode: MERGEPARTIAL native: false - vectorProcessingMode: HASH + vectorProcessingMode: GLOBAL projectedOutputColumnNums: [0] - minReductionHashAggr: 0.99 - mode: hash + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -778,57 +860,68 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cfloat (type: float), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cfloat (type: float), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Group By Operator - aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) - minReductionHashAggr: 0.99 - mode: hash + aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: double), _col3 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (_col0 / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: (_col0 / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / _col1) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -934,84 +1027,109 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 12288 Data size: 1137584 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterDecimal64ColNotEqualDecimal64Scalar(col 13:decimal(13,3)/DECIMAL_64, val 79553)(children: CastLongToDecimal64(col 2:int) -> 13:decimal(13,3)/DECIMAL_64), FilterDoubleColLessDoubleColumn(col 14:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterStringColLikeStringScalar(col 7:string, pattern %b%)) - predicate: ((CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or (cstring2 like '%b%')) (type: boolean) - Statistics: Num rows: 12288 Data size: 1137584 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [3, 4, 0, 15, 18] - selectExpressions: CastLongToDouble(col 3:bigint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 3:bigint) -> 16:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 18:double - Statistics: Num rows: 12288 Data size: 1137584 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col0), count(_col0), sum(_col4), sum(_col3), count(), sum(_col1), min(_col2) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 3:bigint) -> bigint, VectorUDAFCount(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 15:double) -> double, VectorUDAFCountStar(*) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFMinLong(col 0:tinyint) -> tinyint - className: VectorGroupByOperator - groupByMode: HASH - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or (cstring2 like '%b%')) (type: boolean) + Statistics: Num rows: 12288 Data size: 1137584 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterDecimal64ColNotEqualDecimal64Scalar(col 13:decimal(13,3)/DECIMAL_64, val 79553)(children: CastLongToDecimal64(col 2:int) -> 13:decimal(13,3)/DECIMAL_64), FilterDoubleColLessDoubleColumn(col 14:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 14:double), FilterStringColLikeStringScalar(col 7:string, pattern %b%)) + predicate: ((CAST( cint AS decimal(13,3)) <> 79.553) or (UDFToDouble(cbigint) < cdouble) or (cstring2 like '%b%')) (type: boolean) + Statistics: Num rows: 12288 Data size: 1137584 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [3, 4, 0, 15, 18] + selectExpressions: CastLongToDouble(col 3:bigint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 3:bigint) -> 16:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 18:double + Statistics: Num rows: 12288 Data size: 1137584 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), count(_col0), sum(_col4), sum(_col3), count(), sum(_col1), min(_col2) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 3:bigint) -> bigint, VectorUDAFCount(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 15:double) -> double, VectorUDAFCountStar(*) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFMinLong(col 0:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: tinyint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), min(VALUE._col6) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint, VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFSumDouble(col 2:double) -> double, VectorUDAFSumDouble(col 3:double) -> double, VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFMinLong(col 6:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + native: false + vectorProcessingMode: GLOBAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToDouble(_col0) / _col1) (type: double), (- (UDFToDouble(_col0) / _col1)) (type: double), (-6432.0D + (UDFToDouble(_col0) / _col1)) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) + (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), (-6432.0D + (- (-6432.0D + (UDFToDouble(_col0) / _col1)))) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) / (- (-6432.0D + (UDFToDouble(_col0) / _col1)))) (type: double), _col4 (type: bigint), _col5 (type: double), (((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) % power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5)) (type: double), (- ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END)) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) * (- (UDFToDouble(_col0) / _col1))) (type: double), _col6 (type: tinyint), (- _col6) (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [8, 11, 14, 19, 23, 31, 38, 42, 47, 51, 60, 4, 5, 73, 81, 89, 6, 90] + selectExpressions: DoubleColDivideLongColumn(col 7:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 7:double) -> 8:double, DoubleColUnaryMinus(col 10:double)(children: DoubleColDivideLongColumn(col 9:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 9:double) -> 10:double) -> 11:double, DoubleScalarAddDoubleColumn(val -6432.0, col 13:double)(children: DoubleColDivideLongColumn(col 12:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 12:double) -> 13:double) -> 14:double, FuncPowerDoubleToDouble(col 18:double)(children: DoubleColDivideLongColumn(col 17:double, col 1:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 16:double)(children: DoubleColDivideLongColumn(col 15:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 15:double) -> 16:double) -> 17:double) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 22:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 21:double)(children: DoubleColDivideLongColumn(col 20:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 20:double) -> 21:double) -> 22:double) -> 23:double, DoubleColAddDoubleColumn(col 27:double, col 30:double)(children: DoubleColUnaryMinus(col 26:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 24:double) -> 25:double) -> 26:double) -> 27:double, DoubleScalarAddDoubleColumn(val -6432.0, col 29:double)(children: DoubleColDivideLongColumn(col 28:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 28:double) -> 29:double) -> 30:double) -> 31:double, DoubleColDivideLongColumn(col 34:double, col 37:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 33:double)(children: DoubleColDivideLongColumn(col 32:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 32:double) -> 33:double) -> 34:double, IfExprNullCondExpr(col 35:boolean, null, col 36:bigint)(children: LongColEqualLongScalar(col 1:bigint, val 1) -> 35:boolean, LongColSubtractLongScalar(col 1:bigint, val 1) -> 36:bigint) -> 37:bigint) -> 38:double, DoubleColUnaryMinus(col 41:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 40:double)(children: DoubleColDivideLongColumn(col 39:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 39:double) -> 40:double) -> 41:double) -> 42:double, DoubleScalarAddDoubleColumn(val -6432.0, col 46:double)(children: DoubleColUnaryMinus(col 45:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 44:double)(children: DoubleColDivideLongColumn(col 43:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 43:double) -> 44:double) -> 45:double) -> 46:double) -> 47:double, DoubleColUnaryMinus(col 50:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 49:double)(children: DoubleColDivideLongColumn(col 48:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 48:double) -> 49:double) -> 50:double) -> 51:double, DoubleColDivideDoubleColumn(col 55:double, col 59:double)(children: DoubleColUnaryMinus(col 54:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 53:double)(children: DoubleColDivideLongColumn(col 52:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 52:double) -> 53:double) -> 54:double) -> 55:double, DoubleColUnaryMinus(col 58:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 57:double)(children: DoubleColDivideLongColumn(col 56:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 56:double) -> 57:double) -> 58:double) -> 59:double) -> 60:double, DoubleColModuloDoubleColumn(col 67:double, col 72:double)(children: DoubleColDivideLongColumn(col 63:double, col 66:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 62:double)(children: DoubleColDivideLongColumn(col 61:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 61:double) -> 62:double) -> 63:double, IfExprNullCondExpr(col 64:boolean, null, col 65:bigint)(children: LongColEqualLongScalar(col 1:bigint, val 1) -> 64:boolean, LongColSubtractLongScalar(col 1:bigint, val 1) -> 65:bigint) -> 66:bigint) -> 67:double, FuncPowerDoubleToDouble(col 71:double)(children: DoubleColDivideLongColumn(col 70:double, col 1:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 69:double)(children: DoubleColDivideLongColumn(col 68:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 68:double) -> 69:double) -> 70:double) -> 71:double) -> 72:double) -> 73:double, DoubleColUnaryMinus(col 80:double)(children: DoubleColDivideLongColumn(col 76:double, col 79:bigint)(children: DoubleColSubtractDoubleColumn(col 2:double, col 75:double)(children: DoubleColDivideLongColumn(col 74:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 3:double) -> 74:double) -> 75:double) -> 76:double, IfExprNullCondExpr(col 77:boolean, null, col 78:bigint)(children: LongColEqualLongScalar(col 1:bigint, val 1) -> 77:boolean, LongColSubtractLongScalar(col 1:bigint, val 1) -> 78:bigint) -> 79:bigint) -> 80:double) -> 81:double, DoubleColMultiplyDoubleColumn(col 85:double, col 88:double)(children: DoubleColUnaryMinus(col 84:double)(children: DoubleScalarAddDoubleColumn(val -6432.0, col 83:double)(children: DoubleColDivideLongColumn(col 82:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 82:double) -> 83:double) -> 84:double) -> 85:double, DoubleColUnaryMinus(col 87:double)(children: DoubleColDivideLongColumn(col 86:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 86:double) -> 87:double) -> 88:double) -> 89:double, LongColUnaryMinus(col 6:tinyint) -> 90:tinyint + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: tinyint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), min(VALUE._col6) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToDouble(_col0) / _col1) (type: double), (- (UDFToDouble(_col0) / _col1)) (type: double), (-6432.0D + (UDFToDouble(_col0) / _col1)) (type: double), power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) + (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), (-6432.0D + (- (-6432.0D + (UDFToDouble(_col0) / _col1)))) (type: double), (- (-6432.0D + (UDFToDouble(_col0) / _col1))) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) / (- (-6432.0D + (UDFToDouble(_col0) / _col1)))) (type: double), _col4 (type: bigint), _col5 (type: double), (((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END) % power(((_col2 - ((_col3 * _col3) / _col1)) / _col1), 0.5)) (type: double), (- ((_col2 - ((_col3 * _col3) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END)) (type: double), ((- (-6432.0D + (UDFToDouble(_col0) / _col1))) * (- (UDFToDouble(_col0) / _col1))) (type: double), _col6 (type: tinyint), (- _col6) (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 - Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1100,119 +1218,128 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%') or ((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%') or ((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### - Path -> Partition: + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%') or ((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0))) (type: boolean) + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((cstring1 like 'a%') or (cstring1 like 'b%') or (cstring1 like 'c%') or ((length(cstring1) < 50) and (cstring1 like '%n') and (length(cstring1) > 0))) (type: boolean) + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: #### A masked pattern was here #### - Partition - base file name: alltypesparquet - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + Partition + base file name: alltypesparquet + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - name: default.alltypesparquet - name: default.alltypesparquet - Truncated Path -> Alias: - /alltypesparquet [alltypesparquet] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + name: default.alltypesparquet + name: default.alltypesparquet + Truncated Path -> Alias: + /alltypesparquet [alltypesparquet] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -29918,99 +30045,103 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2844090 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + Tez #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11 - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean) + Statistics: Num rows: 12288 Data size: 2844090 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: + Filter Operator + isSamplingPred: false + predicate: (((cint = 49) and (cfloat = 3.5)) or ((cint = 47) and (cfloat = 2.09)) or ((cint = 45) and (cfloat = 3.02))) (type: boolean) + Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 3 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - Path -> Partition: + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11 + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Path -> Alias: #### A masked pattern was here #### - Partition - base file name: alltypesparquet - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + Path -> Partition: #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + Partition + base file name: alltypesparquet + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean +#### A masked pattern was here #### + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - name: default.alltypesparquet - name: default.alltypesparquet - Truncated Path -> Alias: - /alltypesparquet [alltypesparquet] + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + name: default.alltypesparquet + name: default.alltypesparquet + Truncated Path -> Alias: + /alltypesparquet [alltypesparquet] Stage: Stage-0 Fetch Operator @@ -30041,98 +30172,103 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2844090 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean) - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + Tez #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11 - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2844090 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false - MultiFileSpray: false - Path -> Alias: + Filter Operator + isSamplingPred: false + predicate: (struct(cint,cfloat)) IN (const struct(49,3.5), const struct(47,2.09), const struct(45,3.02)) (type: boolean) + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 310 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - Path -> Partition: + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11 + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: llap + LLAP IO: all inputs (cache only) + Path -> Alias: #### A masked pattern was here #### - Partition - base file name: alltypesparquet - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + Path -> Partition: #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + Partition + base file name: alltypesparquet + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean +#### A masked pattern was here #### + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - name: default.alltypesparquet - name: default.alltypesparquet - Truncated Path -> Alias: - /alltypesparquet [alltypesparquet] + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + name: default.alltypesparquet + name: default.alltypesparquet + Truncated Path -> Alias: + /alltypesparquet [alltypesparquet] Stage: Stage-0 Fetch Operator @@ -30163,99 +30299,103 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2844090 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean) - Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE + Tez #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11 - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean) + Statistics: Num rows: 12288 Data size: 2844090 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: + Filter Operator + isSamplingPred: false + predicate: (((cint = 49) or (cfloat = 3.5)) and ((cint = 47) or (cfloat = 2.09)) and ((cint = 45) or (cfloat = 3.02))) (type: boolean) + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - Path -> Partition: + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11 + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Path -> Alias: #### A masked pattern was here #### - Partition - base file name: alltypesparquet - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + Path -> Partition: #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + Partition + base file name: alltypesparquet + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean +#### A masked pattern was here #### + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - name: default.alltypesparquet - name: default.alltypesparquet - Truncated Path -> Alias: - /alltypesparquet [alltypesparquet] + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + name: default.alltypesparquet + name: default.alltypesparquet + Truncated Path -> Alias: + /alltypesparquet [alltypesparquet] Stage: Stage-0 Fetch Operator @@ -30282,199 +30422,157 @@ GROUP BY `cstring1` ORDER BY `cstring1` STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (cstring1) IN ('biology', 'history', 'topology') (type: boolean) - Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (cstring1) IN ('biology', 'history', 'topology') (type: boolean) - Statistics: Num rows: 6 Data size: 470 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: cstring1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: alltypesparquet - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean -#### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + Tez #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - - input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 - columns.comments - columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### - name default.alltypesparquet - numFiles 1 - numRows 12288 - rawDataSize __SOME_NUMBER__ - serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - totalSize __SOME_NUMBER__ + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (cstring1) IN ('biology', 'history', 'topology') (type: boolean) + Statistics: Num rows: 12288 Data size: 862450 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (cstring1) IN ('biology', 'history', 'topology') (type: boolean) + Statistics: Num rows: 6 Data size: 470 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: cstring1 (type: string) + minReductionHashAggr: 0.3333333 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Path -> Alias: #### A masked pattern was here #### - serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe - name: default.alltypesparquet - name: default.alltypesparquet - Truncated Path -> Alias: - /alltypesparquet [alltypesparquet] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 + Path -> Partition: #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + Partition + base file name: alltypesparquet + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 column.name.delimiter , - columns _col0,_col1 - columns.types bigint,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col1 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean +#### A masked pattern was here #### + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - Path -> Partition: + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + + input format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + output format: org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cbigint":"true","cboolean1":"true","cboolean2":"true","cdouble":"true","cfloat":"true","cint":"true","csmallint":"true","cstring1":"true","cstring2":"true","ctimestamp1":"true","ctimestamp2":"true","ctinyint":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ctinyint,csmallint,cint,cbigint,cfloat,cdouble,cstring1,cstring2,ctimestamp1,ctimestamp2,cboolean1,cboolean2 + columns.comments + columns.types tinyint:smallint:int:bigint:float:double:string:string:timestamp:timestamp:boolean:boolean #### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types bigint,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types bigint,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: + name default.alltypesparquet + numFiles 1 + numRows 12288 + rawDataSize __SOME_NUMBER__ + serialization.ddl struct alltypesparquet { byte ctinyint, i16 csmallint, i32 cint, i64 cbigint, float cfloat, double cdouble, string cstring1, string cstring2, timestamp ctimestamp1, timestamp ctimestamp2, bool cboolean1, bool cboolean2} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + totalSize __SOME_NUMBER__ #### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 + serde: org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe + name: default.alltypesparquet + name: default.alltypesparquet + Truncated Path -> Alias: + /alltypesparquet [alltypesparquet] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col1 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE + NumFilesPerFileSink: 1 + Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types bigint:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types bigint:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_1.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_1.q.out new file mode 100644 index 0000000000..3f026e89e2 --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_1.q.out @@ -0,0 +1,211 @@ +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT VAR_POP(ctinyint), + (VAR_POP(ctinyint) / -26.28), + SUM(cfloat), + (-1.389 + SUM(cfloat)), + (SUM(cfloat) * (-1.389 + SUM(cfloat))), + MAX(ctinyint), + (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), + MAX(cint), + (MAX(cint) * 79.553), + VAR_SAMP(cdouble), + (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), + COUNT(cint), + (-563 % MAX(cint)) +FROM alltypesparquet +WHERE (((cdouble > ctinyint) + AND (cboolean2 > 0)) + OR ((cbigint < ctinyint) + OR ((cint > cbigint) + OR (cboolean1 < 0)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT VAR_POP(ctinyint), + (VAR_POP(ctinyint) / -26.28), + SUM(cfloat), + (-1.389 + SUM(cfloat)), + (SUM(cfloat) * (-1.389 + SUM(cfloat))), + MAX(ctinyint), + (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), + MAX(cint), + (MAX(cint) * 79.553), + VAR_SAMP(cdouble), + (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), + COUNT(cint), + (-563 % MAX(cint)) +FROM alltypesparquet +WHERE (((cdouble > ctinyint) + AND (cboolean2 > 0)) + OR ((cbigint < ctinyint) + OR ((cint > cbigint) + OR (cboolean1 < 0)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cboolean1 < 0) or (cbigint < UDFToLong(ctinyint)) or (UDFToLong(cint) > cbigint) or ((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0))) (type: boolean) + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterLongColLessLongScalar(col 10:boolean, val 0), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0))) + predicate: ((cboolean1 < 0) or (cbigint < UDFToLong(ctinyint)) or (UDFToLong(cint) > cbigint) or ((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0))) (type: boolean) + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 4, 2, 5, 14, 17, 18] + selectExpressions: CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 18:double + Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFSumDouble(col 14:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFMaxLong(col 0:tinyint) -> tinyint, VectorUDAFMaxLong(col 2:int) -> int, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint, VectorUDAFCount(col 2:int) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: tinyint), _col5 (type: int), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), max(VALUE._col4), max(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), count(VALUE._col9) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 0:double) -> double, VectorUDAFSumDouble(col 1:double) -> double, VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFSumDouble(col 3:double) -> double, VectorUDAFMaxLong(col 4:tinyint) -> tinyint, VectorUDAFMaxLong(col 5:int) -> int, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFSumDouble(col 7:double) -> double, VectorUDAFCountMerge(col 8:bigint) -> bigint, VectorUDAFCountMerge(col 9:bigint) -> bigint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + native: false + vectorProcessingMode: GLOBAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ((_col0 - ((_col1 * _col1) / _col2)) / _col2) (type: double), (((_col0 - ((_col1 * _col1) / _col2)) / _col2) / -26.28D) (type: double), _col3 (type: double), (-1.389D + _col3) (type: double), (_col3 * (-1.389D + _col3)) (type: double), _col4 (type: tinyint), (- (_col3 * (-1.389D + _col3))) (type: double), _col5 (type: int), (CAST( _col5 AS decimal(10,0)) * 79.553) (type: decimal(16,3)), ((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END) (type: double), (10.175D % (- (_col3 * (-1.389D + _col3)))) (type: double), _col9 (type: bigint), (-563 % _col5) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [13, 18, 3, 19, 21, 4, 24, 5, 27, 34, 38, 9, 39] + selectExpressions: DoubleColDivideLongColumn(col 12:double, col 2:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 10:double) -> 11:double) -> 12:double) -> 13:double, DoubleColDivideDoubleScalar(col 17:double, val -26.28)(children: DoubleColDivideLongColumn(col 16:double, col 2:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 14:double) -> 15:double) -> 16:double) -> 17:double) -> 18:double, DoubleScalarAddDoubleColumn(val -1.389, col 3:double) -> 19:double, DoubleColMultiplyDoubleColumn(col 3:double, col 20:double)(children: DoubleScalarAddDoubleColumn(val -1.389, col 3:double) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 23:double)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 22:double)(children: DoubleScalarAddDoubleColumn(val -1.389, col 3:double) -> 22:double) -> 23:double) -> 24:double, DecimalColMultiplyDecimalScalar(col 26:decimal(10,0), val 79.553)(children: CastLongToDecimal(col 5:int) -> 26:decimal(10,0)) -> 27:decimal(16,3), DoubleColDivideLongColumn(col 30:double, col 33:bigint)(children: DoubleColSubtractDoubleColumn(col 6:double, col 29:double)(children: DoubleColDivideLongColumn(col 28:double, col 8:bigint)(children: DoubleColMultiplyDoubleColumn(col 7:double, col 7:double) -> 28:double) -> 29:double) -> 30:double, IfExprNullCondExpr(col 31:boolean, null, col 32:bigint)(children: LongColEqualLongScalar(col 8:bigint, val 1) -> 31:boolean, LongColSubtractLongScalar(col 8:bigint, val 1) -> 32:bigint) -> 33:bigint) -> 34:double, DoubleScalarModuloDoubleColumn(val 10.175, col 37:double)(children: DoubleColUnaryMinus(col 36:double)(children: DoubleColMultiplyDoubleColumn(col 3:double, col 35:double)(children: DoubleScalarAddDoubleColumn(val -1.389, col 3:double) -> 35:double) -> 36:double) -> 37:double) -> 38:double, LongScalarModuloLongColumn(val -563, col 5:int) -> 39:int + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT VAR_POP(ctinyint), + (VAR_POP(ctinyint) / -26.28), + SUM(cfloat), + (-1.389 + SUM(cfloat)), + (SUM(cfloat) * (-1.389 + SUM(cfloat))), + MAX(ctinyint), + (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), + MAX(cint), + (MAX(cint) * 79.553), + VAR_SAMP(cdouble), + (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), + COUNT(cint), + (-563 % MAX(cint)) +FROM alltypesparquet +WHERE (((cdouble > ctinyint) + AND (cboolean2 > 0)) + OR ((cbigint < ctinyint) + OR ((cint > cbigint) + OR (cboolean1 < 0)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT VAR_POP(ctinyint), + (VAR_POP(ctinyint) / -26.28), + SUM(cfloat), + (-1.389 + SUM(cfloat)), + (SUM(cfloat) * (-1.389 + SUM(cfloat))), + MAX(ctinyint), + (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), + MAX(cint), + (MAX(cint) * 79.553), + VAR_SAMP(cdouble), + (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), + COUNT(cint), + (-563 % MAX(cint)) +FROM alltypesparquet +WHERE (((cdouble > ctinyint) + AND (cboolean2 > 0)) + OR ((cbigint < ctinyint) + OR ((cint > cbigint) + OR (cboolean1 < 0)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +1074.8302575472321 -40.899172661614614 -21997.674998402596 -21999.063998402595 4.839282601059194E8 62 -4.839282601059194E8 1073680599 85414512692.247 7.569848642620917E10 10.175 3745 -563 diff --git ql/src/test/results/clientpositive/parquet_vectorization_10.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_10.q.out similarity index 85% rename from ql/src/test/results/clientpositive/parquet_vectorization_10.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_10.q.out index aef4ad2cec..e3c51a5ccd 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_10.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_10.q.out @@ -60,50 +60,54 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimal64ColLessEqualDecimal64Scalar(col 14:decimal(6,2)/DECIMAL_64, val -563815)(children: CastLongToDecimal64(col 0:tinyint) -> 14:decimal(6,2)/DECIMAL_64)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterStringColLikeStringScalar(col 6:string, pattern %a))) - predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and (cstring1 like '%a'))) (type: boolean) - Statistics: Num rows: 11590 Data size: 2232584 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [5, 8, 0, 10, 6, 15, 17, 20, 21, 23, 24, 25, 27, 30, 32] - selectExpressions: DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 17:double, DoubleColModuloDoubleScalar(col 19:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 18:double)(children: CastLongToDouble(col 1:smallint) -> 18:double) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 5:double) -> 21:double, DoubleColModuloDoubleColumn(col 22:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 22:double) -> 23:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 24:smallint, DoubleColUnaryMinus(col 5:double) -> 25:double, LongColMultiplyLongColumn(col 3:bigint, col 26:bigint)(children: LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 26:smallint) -> 27:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 29:double)(children: DoubleColAddDoubleColumn(col 5:double, col 28:double)(children: CastLongToDouble(col 1:smallint) -> 28:double) -> 29:double) -> 30:double, DoubleColUnaryMinus(col 31:double)(children: DoubleColUnaryMinus(col 5:double) -> 31:double) -> 32:double - Statistics: Num rows: 11590 Data size: 2178896 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 11590 Data size: 2178896 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and (cstring1 like '%a'))) (type: boolean) + Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterStringGroupColLessEqualStringScalar(col 7:string, val 10), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterDecimal64ColLessEqualDecimal64Scalar(col 14:decimal(6,2)/DECIMAL_64, val -563815)(children: CastLongToDecimal64(col 0:tinyint) -> 14:decimal(6,2)/DECIMAL_64)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 6981.0), FilterStringColLikeStringScalar(col 6:string, pattern %a))) + predicate: ((cstring2 <= '10') or ((UDFToDouble(ctinyint) > cdouble) and (CAST( ctinyint AS decimal(6,2)) <= -5638.15)) or ((cdouble > 6981.0D) and (cstring1 like '%a'))) (type: boolean) + Statistics: Num rows: 11590 Data size: 2232584 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cdouble (type: double), ctimestamp1 (type: timestamp), ctinyint (type: tinyint), cboolean1 (type: boolean), cstring1 (type: string), (- cdouble) (type: double), (cdouble + UDFToDouble(csmallint)) (type: double), ((cdouble + UDFToDouble(csmallint)) % 33.0D) (type: double), (- cdouble) (type: double), (UDFToDouble(ctinyint) % cdouble) (type: double), (UDFToShort(ctinyint) % csmallint) (type: smallint), (- cdouble) (type: double), (cbigint * UDFToLong((UDFToShort(ctinyint) % csmallint))) (type: bigint), (9763215.5639D - (cdouble + UDFToDouble(csmallint))) (type: double), (- (- cdouble)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [5, 8, 0, 10, 6, 15, 17, 20, 21, 23, 24, 25, 27, 30, 32] + selectExpressions: DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleColumn(col 5:double, col 16:double)(children: CastLongToDouble(col 1:smallint) -> 16:double) -> 17:double, DoubleColModuloDoubleScalar(col 19:double, val 33.0)(children: DoubleColAddDoubleColumn(col 5:double, col 18:double)(children: CastLongToDouble(col 1:smallint) -> 18:double) -> 19:double) -> 20:double, DoubleColUnaryMinus(col 5:double) -> 21:double, DoubleColModuloDoubleColumn(col 22:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 22:double) -> 23:double, LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 24:smallint, DoubleColUnaryMinus(col 5:double) -> 25:double, LongColMultiplyLongColumn(col 3:bigint, col 26:bigint)(children: LongColModuloLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint) -> 26:smallint) -> 27:bigint, DoubleScalarSubtractDoubleColumn(val 9763215.5639, col 29:double)(children: DoubleColAddDoubleColumn(col 5:double, col 28:double)(children: CastLongToDouble(col 1:smallint) -> 28:double) -> 29:double) -> 30:double, DoubleColUnaryMinus(col 31:double)(children: DoubleColUnaryMinus(col 5:double) -> 31:double) -> 32:double + Statistics: Num rows: 11590 Data size: 2178896 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 11590 Data size: 2178896 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_vectorization_11.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_11.q.out similarity index 62% rename from ql/src/test/results/clientpositive/parquet_vectorization_11.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_11.q.out index 5603015358..8987304922 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_11.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_11.q.out @@ -42,50 +42,54 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((ctimestamp1 is null and (cstring1 like '%a')) or (cstring2 = cstring1)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2256914 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterStringColLikeStringScalar(col 6:string, pattern %a)), FilterStringGroupColEqualStringGroupColumn(col 7:string, col 6:string)) - predicate: ((ctimestamp1 is null and (cstring1 like '%a')) or (cstring2 = cstring1)) (type: boolean) - Statistics: Num rows: 7701 Data size: 1414500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639D) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0D) (type: double), (cdouble * -5638.15D) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [6, 10, 5, 8, 13, 14, 15, 17, 18] - selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1:int)(children: col 1:smallint) -> 13:int, DoubleColSubtractDoubleScalar(col 5:double, val 9763215.5639) -> 14:double, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleScalar(col 16:double, val 6981.0)(children: DoubleColUnaryMinus(col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleScalar(col 5:double, val -5638.15) -> 18:double - Statistics: Num rows: 7701 Data size: 1116736 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 7701 Data size: 1116736 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((ctimestamp1 is null and (cstring1 like '%a')) or (cstring2 = cstring1)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2256914 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: SelectColumnIsNull(col 8:timestamp), FilterStringColLikeStringScalar(col 6:string, pattern %a)), FilterStringGroupColEqualStringGroupColumn(col 7:string, col 6:string)) + predicate: ((ctimestamp1 is null and (cstring1 like '%a')) or (cstring2 = cstring1)) (type: boolean) + Statistics: Num rows: 7701 Data size: 1414500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), ctimestamp1 (type: timestamp), (-3728 * UDFToInteger(csmallint)) (type: int), (cdouble - 9763215.5639D) (type: double), (- cdouble) (type: double), ((- cdouble) + 6981.0D) (type: double), (cdouble * -5638.15D) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [6, 10, 5, 8, 13, 14, 15, 17, 18] + selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 1:int)(children: col 1:smallint) -> 13:int, DoubleColSubtractDoubleScalar(col 5:double, val 9763215.5639) -> 14:double, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleColAddDoubleScalar(col 16:double, val 6981.0)(children: DoubleColUnaryMinus(col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleScalar(col 5:double, val -5638.15) -> 18:double + Statistics: Num rows: 7701 Data size: 1116736 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 7701 Data size: 1116736 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_vectorization_12.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_12.q.out similarity index 88% rename from ql/src/test/results/clientpositive/parquet_vectorization_12.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_12.q.out index 79a2f81a7c..26f126c0d5 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_12.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_12.q.out @@ -72,137 +72,148 @@ PLAN VECTORIZATION: STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ctimestamp1 is null) (type: boolean) - Statistics: Num rows: 12288 Data size: 1522994 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %a), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11:boolean, val 1), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 1:bigint)(children: col 1:smallint))), FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10:boolean, col 11:boolean), FilterLongColNotEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint)), SelectColumnIsNull(col 8:timestamp)) - predicate: (((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ctimestamp1 is null) (type: boolean) - Statistics: Num rows: 1903 Data size: 236052 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ctimestamp1 is null) (type: boolean) + Statistics: Num rows: 12288 Data size: 1522994 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %a), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 11:boolean, val 1), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 1:bigint)(children: col 1:smallint))), FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 10:boolean, col 11:boolean), FilterLongColNotEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint)), SelectColumnIsNull(col 8:timestamp)) + predicate: (((cstring1 like '%a') or ((cboolean2 <= 1) and (cbigint >= UDFToLong(csmallint)))) and ((cboolean1 >= cboolean2) or (UDFToShort(ctinyint) <> csmallint)) and ctimestamp1 is null) (type: boolean) + Statistics: Num rows: 1903 Data size: 236052 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint), cboolean1 (type: boolean), cstring1 (type: string), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), (cdouble * cdouble) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [3, 10, 6, 5, 13, 16, 17] + selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 17:double + Statistics: Num rows: 1903 Data size: 236052 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col0), sum(_col5), sum(_col4), sum(_col3), count(_col3), sum(_col0), sum(_col6) + Group By Vectorization: + aggregators: VectorUDAFCount(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 16:double) -> double, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint, VectorUDAFSumLong(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 17:double) -> double + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 5:double, col 3:bigint, col 6:string, col 10:boolean + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] + keys: _col3 (type: double), _col0 (type: bigint), _col2 (type: string), _col1 (type: boolean) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 1903 Data size: 268676 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) + null sort order: zzzz + sort order: ++++ + Map-reduce partition columns: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1903 Data size: 268676 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFSumDouble(col 7:double) -> double, VectorUDAFCountMerge(col 8:bigint) -> bigint, VectorUDAFSumLong(col 9:bigint) -> bigint, VectorUDAFSumDouble(col 10:double) -> double + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:double, col 1:bigint, col 2:string, col 3:boolean + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] + keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 1903 Data size: 268676 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0D * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) (type: double), ((-6432.0D * _col0) / -6432.0D) (type: double), (- ((-6432.0D * _col0) / -6432.0D)) (type: double), (_col7 / _col8) (type: double), (- (-6432.0D * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col9 (type: bigint), ((_col7 / _col8) / (-6432.0D * _col0)) (type: double), (- (- ((-6432.0D * _col0) / -6432.0D))) (type: double), (((-6432.0D * _col0) / -6432.0D) + (- (-6432.0D * _col0))) (type: double), power(((_col10 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 3, 2, 0, 11, 12, 4, 13, 21, 23, 26, 27, 29, 31, 9, 34, 38, 43, 48] + selectExpressions: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 11:double, LongColUnaryMinus(col 1:bigint) -> 12:bigint, LongColMultiplyLongColumn(col 1:bigint, col 4:bigint) -> 13:bigint, FuncPowerDoubleToDouble(col 20:double)(children: DoubleColDivideLongColumn(col 16:double, col 19:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 4:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 14:double) -> 15:double) -> 16:double, IfExprNullCondExpr(col 17:boolean, null, col 18:bigint)(children: LongColEqualLongScalar(col 4:bigint, val 1) -> 17:boolean, LongColSubtractLongScalar(col 4:bigint, val 1) -> 18:bigint) -> 19:bigint) -> 20:double) -> 21:double, DoubleColDivideDoubleScalar(col 22:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 22:double) -> 23:double, DoubleColUnaryMinus(col 25:double)(children: DoubleColDivideDoubleScalar(col 24:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 24:double) -> 25:double) -> 26:double, DoubleColDivideLongColumn(col 7:double, col 8:bigint) -> 27:double, DoubleColUnaryMinus(col 28:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 28:double) -> 29:double, DecimalScalarAddDecimalColumn(val -5638.15, col 30:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 30:decimal(19,0)) -> 31:decimal(22,2), DoubleColDivideDoubleColumn(col 32:double, col 33:double)(children: DoubleColDivideLongColumn(col 7:double, col 8:bigint) -> 32:double, DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 33:double) -> 34:double, DoubleColUnaryMinus(col 37:double)(children: DoubleColUnaryMinus(col 36:double)(children: DoubleColDivideDoubleScalar(col 35:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 35:double) -> 36:double) -> 37:double) -> 38:double, DoubleColAddDoubleColumn(col 40:double, col 42:double)(children: DoubleColDivideDoubleScalar(col 39:double, val -6432.0)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 39:double) -> 40:double, DoubleColUnaryMinus(col 41:double)(children: DoubleScalarMultiplyDoubleColumn(val -6432.0, col 0:double) -> 41:double) -> 42:double) -> 43:double, FuncPowerDoubleToDouble(col 47:double)(children: DoubleColDivideLongColumn(col 46:double, col 8:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 45:double)(children: DoubleColDivideLongColumn(col 44:double, col 8:bigint)(children: DoubleColMultiplyDoubleColumn(col 7:double, col 7:double) -> 44:double) -> 45:double) -> 46:double) -> 47:double) -> 48:double + Statistics: Num rows: 1903 Data size: 603604 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: double), _col0 (type: bigint), _col2 (type: string) + null sort order: zzz + sort order: +++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1903 Data size: 603604 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) + Reducer 3 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Select Operator - expressions: cbigint (type: bigint), cboolean1 (type: boolean), cstring1 (type: string), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double), (cdouble * cdouble) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: string), null (type: timestamp), KEY.reducesinkkey0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(22,2)), VALUE._col11 (type: bigint), VALUE._col12 (type: double), VALUE._col8 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [3, 10, 6, 5, 13, 16, 17] - selectExpressions: CastLongToDouble(col 3:bigint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, CastLongToDouble(col 3:bigint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 17:double - Statistics: Num rows: 1903 Data size: 236052 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col0), sum(_col5), sum(_col4), sum(_col3), count(_col3), sum(_col0), sum(_col6) - Group By Vectorization: - aggregators: VectorUDAFCount(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 16:double) -> double, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint, VectorUDAFSumLong(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 17:double) -> double - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 5:double, col 3:bigint, col 6:string, col 10:boolean + projectedOutputColumnNums: [1, 3, 2, 19, 0, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 11, 16, 17, 18] + selectExpressions: ConstantVectorExpression(val null) -> 19:timestamp + Statistics: Num rows: 1903 Data size: 603644 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] - keys: _col3 (type: double), _col0 (type: bigint), _col2 (type: string), _col1 (type: boolean) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1903 Data size: 268676 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) - null sort order: zzzz - sort order: ++++ - Map-reduce partition columns: _col0 (type: double), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1903 Data size: 268676 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) - keys: KEY._col0 (type: double), KEY._col1 (type: bigint), KEY._col2 (type: string), KEY._col3 (type: boolean) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 1903 Data size: 268676 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint), _col3 (type: boolean), _col2 (type: string), _col0 (type: double), (-6432.0D * _col0) (type: double), (- _col1) (type: bigint), _col4 (type: bigint), (_col1 * _col4) (type: bigint), power(((_col5 - ((_col6 * _col6) / _col4)) / CASE WHEN ((_col4 = 1L)) THEN (null) ELSE ((_col4 - 1)) END), 0.5) (type: double), ((-6432.0D * _col0) / -6432.0D) (type: double), (- ((-6432.0D * _col0) / -6432.0D)) (type: double), (_col7 / _col8) (type: double), (- (-6432.0D * _col0)) (type: double), (-5638.15 + CAST( _col1 AS decimal(19,0))) (type: decimal(22,2)), _col9 (type: bigint), ((_col7 / _col8) / (-6432.0D * _col0)) (type: double), (- (- ((-6432.0D * _col0) / -6432.0D))) (type: double), (((-6432.0D * _col0) / -6432.0D) + (- (-6432.0D * _col0))) (type: double), power(((_col10 - ((_col7 * _col7) / _col8)) / _col8), 0.5) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 1903 Data size: 603604 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - Reduce Output Operator - key expressions: _col3 (type: double), _col0 (type: bigint), _col2 (type: string) - null sort order: zzz - sort order: +++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1903 Data size: 603604 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: decimal(22,2)), _col14 (type: bigint), _col15 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: string), null (type: timestamp), KEY.reducesinkkey0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: bigint), VALUE._col3 (type: bigint), VALUE._col4 (type: bigint), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(22,2)), VALUE._col11 (type: bigint), VALUE._col12 (type: double), VALUE._col8 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1903 Data size: 603644 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1903 Data size: 603644 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1903 Data size: 603644 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_13.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_13.q.out new file mode 100644 index 0000000000..5eee33fade --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_13.q.out @@ -0,0 +1,716 @@ +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28789) + AND ((ctimestamp2 != -28788) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28789) + AND ((ctimestamp2 != -28788) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) + Statistics: Num rows: 12288 Data size: 1779902 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28789.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28788.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimal64ColLessDecimal64Scalar(col 15:decimal(11,4)/DECIMAL_64, val 97632155639)(children: CastLongToDecimal64(col 0:tinyint) -> 15:decimal(11,4)/DECIMAL_64))) + predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) + Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: +++++ + keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + null sort order: zzzzz + Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE + top n: 40 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 10:boolean, col 0:tinyint, col 8:timestamp, col 4:float, col 6:string + native: true + Select Operator + expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 14, 18] + selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double + Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 0:tinyint) -> tinyint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 14:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFMaxDouble(col 4:float) -> float, VectorUDAFMinLong(col 0:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 10:boolean, col 0:tinyint, col 8:timestamp, col 4:float, col 6:string + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + null sort order: zzzzz + sort order: +++++ + Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 5:tinyint) -> tinyint, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFSumDouble(col 7:double) -> double, VectorUDAFSumDouble(col 8:double) -> double, VectorUDAFCountMerge(col 9:bigint) -> bigint, VectorUDAFSumDouble(col 10:double) -> double, VectorUDAFSumDouble(col 11:double) -> double, VectorUDAFCountMerge(col 12:bigint) -> bigint, VectorUDAFMaxDouble(col 13:float) -> float, VectorUDAFMinLong(col 14:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:boolean, col 1:tinyint, col 2:timestamp, col 3:float, col 4:string + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: +++++++++++++++++++++ + keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) + null sort order: zzzzzzzzzzzzzzzzzzzzz + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + top n: 40 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 0:boolean, col 1:tinyint, col 2:timestamp, col 3:float, col 4:string, LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, col 5:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, col 6:double, DoubleColMultiplyDoubleColumn(col 6:double, col 20:double)(children: CastLongToDouble(col 19:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 19:tinyint) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 6:double) -> 22:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 23:float, FuncPowerDoubleToDouble(col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 24:double) -> 25:double) -> 26:double) -> 27:double) -> 28:double, DoubleColUnaryMinus(col 6:double) -> 29:double, FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 32:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 30:double) -> 31:double) -> 32:double) -> 33:double) -> 34:double, DecimalColSubtractDecimalScalar(col 37:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 36:tinyint)(children: LongColAddLongColumn(col 35:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 35:tinyint) -> 36:tinyint) -> 37:decimal(3,0)) -> 38:decimal(7,3), DoubleColUnaryMinus(col 39:double)(children: DoubleColUnaryMinus(col 6:double) -> 39:double) -> 40:double, DoubleScalarDivideDoubleColumn(val -26.28, col 42:double)(children: DoubleColUnaryMinus(col 41:double)(children: DoubleColUnaryMinus(col 6:double) -> 41:double) -> 42:double) -> 43:double, col 13:float, DoubleColDivideDoubleColumn(col 47:double, col 48:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 46:double)(children: CastLongToDouble(col 45:tinyint)(children: LongColAddLongColumn(col 44:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 44:tinyint) -> 45:tinyint) -> 46:double) -> 47:double, CastLongToDouble(col 1:tinyint) -> 48:double) -> 49:double, col 14:tinyint + native: true + Select Operator + expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 16, 5, 19, 6, 24, 20, 25, 26, 27, 30, 50, 32, 31, 13, 41, 14] + selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint, LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 19:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 20:double)(children: CastLongToDouble(col 35:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 35:tinyint) -> 20:double) -> 24:double, DoubleColUnaryMinus(col 6:double) -> 20:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 25:float, FuncPowerDoubleToDouble(col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 26:double) -> 27:double) -> 26:double) -> 27:double) -> 26:double, DoubleColUnaryMinus(col 6:double) -> 27:double, FuncPowerDoubleToDouble(col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 30:double) -> 31:double) -> 30:double) -> 31:double) -> 30:double, DecimalColSubtractDecimalScalar(col 37:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 35:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 35:tinyint) -> 37:decimal(3,0)) -> 50:decimal(7,3), DoubleColUnaryMinus(col 31:double)(children: DoubleColUnaryMinus(col 6:double) -> 31:double) -> 32:double, DoubleScalarDivideDoubleColumn(val -26.28, col 33:double)(children: DoubleColUnaryMinus(col 31:double)(children: DoubleColUnaryMinus(col 6:double) -> 31:double) -> 33:double) -> 31:double, DoubleColDivideDoubleColumn(col 39:double, col 33:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 33:double)(children: CastLongToDouble(col 35:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 35:tinyint) -> 33:double) -> 39:double, CastLongToDouble(col 1:tinyint) -> 33:double) -> 41:double + Statistics: Num rows: 693 Data size: 142976 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) + null sort order: zzzzzzzzzzzzzzzzzzzzz + sort order: +++++++++++++++++++++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 693 Data size: 142976 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Reducer 3 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] + Statistics: Num rows: 693 Data size: 142976 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 40 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 40 Data size: 8466 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 40 Data size: 8466 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 40 + Processor Tree: + ListSink + +PREHOOK: query: SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28789) + AND ((ctimestamp2 != -28788) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28789) + AND ((ctimestamp2 != -28788) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +true -55 1969-12-31 16:00:12.297 -55.0 1cGVWH7n1QU 55 -55 0 -55.0 -0.0 55.0 -4375.415 0.0 55.0 0.0 -10.175 -55.0 0.47781818181818186 -55.0 0.0 -55 +true -55 1969-12-31 16:00:13.15 -55.0 1cGVWH7n1QU 55 -55 0 -55.0 -0.0 55.0 -4375.415 0.0 55.0 0.0 -10.175 -55.0 0.47781818181818186 -55.0 0.0 -55 +true -56 1969-12-31 16:00:11.242 -56.0 cvLH6Eat2yFsyy7p 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 +true -56 1969-12-31 16:00:13.534 -56.0 1cGVWH7n1QU 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 +true -56 1969-12-31 16:00:14.038 -56.0 1cGVWH7n1QU 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 +true -56 1969-12-31 16:00:14.689 -56.0 cvLH6Eat2yFsyy7p 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 +true -56 1969-12-31 16:00:16.37 -56.0 cvLH6Eat2yFsyy7p 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 +true -57 1969-12-31 16:00:11.534 -57.0 cvLH6Eat2yFsyy7p 57 -57 0 -57.0 -0.0 57.0 -4534.521 0.0 57.0 0.0 -10.175 -57.0 0.4610526315789474 -57.0 0.0 -57 +true -57 1969-12-31 16:00:13.365 -57.0 1cGVWH7n1QU 57 -57 0 -57.0 -0.0 57.0 -4534.521 0.0 57.0 0.0 -10.175 -57.0 0.4610526315789474 -57.0 0.0 -57 +true -57 1969-12-31 16:00:14.225 -57.0 821UdmGbkEf4j 57 -57 0 -57.0 -0.0 57.0 -4534.521 0.0 57.0 0.0 -10.175 -57.0 0.4610526315789474 -57.0 0.0 -57 +true -58 1969-12-31 16:00:12.918 -58.0 cvLH6Eat2yFsyy7p 58 -58 0 -58.0 -0.0 58.0 -4614.074 0.0 58.0 0.0 -10.175 -58.0 0.4531034482758621 -58.0 0.0 -58 +true -58 1969-12-31 16:00:13.209 -58.0 cvLH6Eat2yFsyy7p 58 -58 0 -58.0 -0.0 58.0 -4614.074 0.0 58.0 0.0 -10.175 -58.0 0.4531034482758621 -58.0 0.0 -58 +true -58 1969-12-31 16:00:14.933 -58.0 cvLH6Eat2yFsyy7p 58 -58 0 -58.0 -0.0 58.0 -4614.074 0.0 58.0 0.0 -10.175 -58.0 0.4531034482758621 -58.0 0.0 -58 +true -59 1969-12-31 16:00:11.065 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:11.109 -59.0 1cGVWH7n1QU 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:11.231 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:11.758 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:12.227 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:15.242 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:15.278 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:16.069 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -59 1969-12-31 16:00:16.125 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 +true -60 1969-12-31 16:00:11.849 -60.0 1cGVWH7n1QU 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 +true -60 1969-12-31 16:00:12.223 -60.0 1cGVWH7n1QU 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 +true -60 1969-12-31 16:00:12.291 -60.0 821UdmGbkEf4j 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 +true -60 1969-12-31 16:00:13.567 -60.0 821UdmGbkEf4j 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 +true -60 1969-12-31 16:00:15.188 -60.0 cvLH6Eat2yFsyy7p 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 +true -60 1969-12-31 16:00:16.165 -60.0 cvLH6Eat2yFsyy7p 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 +true -61 1969-12-31 16:00:12.045 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:12.75 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:15.325 -61.0 821UdmGbkEf4j 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:15.694 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -62 1969-12-31 16:00:13.677 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:14.872 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:15.153 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -63 1969-12-31 16:00:13.752 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -63 1969-12-31 16:00:14.899 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -63 1969-12-31 16:00:15.827 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -64 1969-12-31 16:00:11.952 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:12.857 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28801.388) + AND ((ctimestamp2 != -28801.3359999999999999) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28801.388) + AND ((ctimestamp2 != -28801.3359999999999999) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) + Statistics: Num rows: 12288 Data size: 1779902 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28801.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28801.336)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimal64ColLessDecimal64Scalar(col 15:decimal(11,4)/DECIMAL_64, val 97632155639)(children: CastLongToDecimal64(col 0:tinyint) -> 15:decimal(11,4)/DECIMAL_64))) + predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) + Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: +++++ + keys: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) + null sort order: zzzzz + Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE + top n: 40 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 10:boolean, col 0:tinyint, col 8:timestamp, col 4:float, col 6:string + native: true + Select Operator + expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 13, 14, 18] + selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 0:tinyint) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double) -> 18:double + Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 0:tinyint) -> tinyint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 14:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFMaxDouble(col 4:float) -> float, VectorUDAFMinLong(col 0:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 10:boolean, col 0:tinyint, col 8:timestamp, col 4:float, col 6:string + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + null sort order: zzzzz + sort order: +++++ + Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 5:tinyint) -> tinyint, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFSumDouble(col 7:double) -> double, VectorUDAFSumDouble(col 8:double) -> double, VectorUDAFCountMerge(col 9:bigint) -> bigint, VectorUDAFSumDouble(col 10:double) -> double, VectorUDAFSumDouble(col 11:double) -> double, VectorUDAFCountMerge(col 12:bigint) -> bigint, VectorUDAFMaxDouble(col 13:float) -> float, VectorUDAFMinLong(col 14:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:boolean, col 1:tinyint, col 2:timestamp, col 3:float, col 4:string + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: +++++++++++++++++++++ + keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) + null sort order: zzzzzzzzzzzzzzzzzzzzz + Statistics: Num rows: 693 Data size: 97202 Basic stats: COMPLETE Column stats: COMPLETE + top n: 40 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 0:boolean, col 1:tinyint, col 2:timestamp, col 3:float, col 4:string, LongColUnaryMinus(col 1:tinyint) -> 15:tinyint, col 5:tinyint, LongColAddLongColumn(col 16:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint) -> 17:tinyint, col 6:double, DoubleColMultiplyDoubleColumn(col 6:double, col 20:double)(children: CastLongToDouble(col 19:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 19:tinyint) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 6:double) -> 22:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 23:float, FuncPowerDoubleToDouble(col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 24:double) -> 25:double) -> 26:double) -> 27:double) -> 28:double, DoubleColUnaryMinus(col 6:double) -> 29:double, FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 32:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 30:double) -> 31:double) -> 32:double) -> 33:double) -> 34:double, DecimalColSubtractDecimalScalar(col 37:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 36:tinyint)(children: LongColAddLongColumn(col 35:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 35:tinyint) -> 36:tinyint) -> 37:decimal(3,0)) -> 38:decimal(7,3), DoubleColUnaryMinus(col 39:double)(children: DoubleColUnaryMinus(col 6:double) -> 39:double) -> 40:double, DoubleScalarDivideDoubleColumn(val -26.28, col 42:double)(children: DoubleColUnaryMinus(col 41:double)(children: DoubleColUnaryMinus(col 6:double) -> 41:double) -> 42:double) -> 43:double, col 13:float, DoubleColDivideDoubleColumn(col 47:double, col 48:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 46:double)(children: CastLongToDouble(col 45:tinyint)(children: LongColAddLongColumn(col 44:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 44:tinyint) -> 45:tinyint) -> 46:double) -> 47:double, CastLongToDouble(col 1:tinyint) -> 48:double) -> 49:double, col 14:tinyint + native: true + Select Operator + expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 16, 5, 19, 6, 24, 20, 25, 26, 27, 30, 50, 32, 31, 13, 41, 14] + selectExpressions: LongColUnaryMinus(col 1:tinyint) -> 16:tinyint, LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 19:tinyint, DoubleColMultiplyDoubleColumn(col 6:double, col 20:double)(children: CastLongToDouble(col 35:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 35:tinyint) -> 20:double) -> 24:double, DoubleColUnaryMinus(col 6:double) -> 20:double, DoubleScalarMultiplyDoubleColumn(val 79.5530014038086, col 3:float) -> 25:float, FuncPowerDoubleToDouble(col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColSubtractDoubleColumn(col 7:double, col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 9:bigint)(children: DoubleColMultiplyDoubleColumn(col 8:double, col 8:double) -> 26:double) -> 27:double) -> 26:double) -> 27:double) -> 26:double, DoubleColUnaryMinus(col 6:double) -> 27:double, FuncPowerDoubleToDouble(col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColSubtractDoubleColumn(col 10:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 12:bigint)(children: DoubleColMultiplyDoubleColumn(col 11:double, col 11:double) -> 30:double) -> 31:double) -> 30:double) -> 31:double) -> 30:double, DecimalColSubtractDecimalScalar(col 37:decimal(3,0), val 10.175)(children: CastLongToDecimal(col 35:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 35:tinyint) -> 37:decimal(3,0)) -> 50:decimal(7,3), DoubleColUnaryMinus(col 31:double)(children: DoubleColUnaryMinus(col 6:double) -> 31:double) -> 32:double, DoubleScalarDivideDoubleColumn(val -26.28, col 33:double)(children: DoubleColUnaryMinus(col 31:double)(children: DoubleColUnaryMinus(col 6:double) -> 31:double) -> 33:double) -> 31:double, DoubleColDivideDoubleColumn(col 39:double, col 33:double)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 33:double)(children: CastLongToDouble(col 35:tinyint)(children: LongColAddLongColumn(col 18:tinyint, col 5:tinyint)(children: LongColUnaryMinus(col 1:tinyint) -> 18:tinyint) -> 35:tinyint) -> 33:double) -> 39:double, CastLongToDouble(col 1:tinyint) -> 33:double) -> 41:double + Statistics: Num rows: 693 Data size: 142976 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) + null sort order: zzzzzzzzzzzzzzzzzzzzz + sort order: +++++++++++++++++++++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 693 Data size: 142976 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Reducer 3 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 10, 14, 15, 16, 17, 18, 19, 20] + Statistics: Num rows: 693 Data size: 142976 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 40 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 40 Data size: 8466 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 40 Data size: 8466 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 40 + Processor Tree: + ListSink + +PREHOOK: query: SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28801.388) + AND ((ctimestamp2 != -28801.3359999999999999) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT cboolean1, + ctinyint, + ctimestamp1, + cfloat, + cstring1, + (-(ctinyint)) as c1, + MAX(ctinyint) as c2, + ((-(ctinyint)) + MAX(ctinyint)) as c3, + SUM(cfloat) as c4, + (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, + (-(SUM(cfloat))) as c6, + (79.553 * cfloat) as c7, + STDDEV_POP(cfloat) as c8, + (-(SUM(cfloat))) as c9, + STDDEV_POP(ctinyint) as c10, + (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, + (-((-(SUM(cfloat))))) as c12, + (-26.28 / (-((-(SUM(cfloat)))))) as c13, + MAX(cfloat) as c14, + ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, + MIN(ctinyint) as c16 +FROM alltypesparquet +WHERE (((cfloat < 3569) + AND ((10.175 >= cdouble) + AND (cboolean1 != 1))) + OR ((ctimestamp1 > -28801.388) + AND ((ctimestamp2 != -28801.3359999999999999) + AND (ctinyint < 9763215.5639)))) +GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 +ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 +LIMIT 40 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +true -61 1969-12-31 16:00:00.554 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:02.339 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:02.497 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:03.742 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:07.538 -61.0 821UdmGbkEf4j 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:09.809 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:10.713 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:12.045 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -61 1969-12-31 16:00:12.75 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 +true -62 1969-12-31 16:00:00.337 -62.0 1cGVWH7n1QU 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:00.659 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:00.684 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:01.419 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:02.123 -62.0 1cGVWH7n1QU 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:02.922 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:04.978 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:07.756 -62.0 1cGVWH7n1QU 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:07.847 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:07.903 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:13.677 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:14.872 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -62 1969-12-31 16:00:15.153 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 +true -63 1969-12-31 16:00:05.654 -63.0 821UdmGbkEf4j 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -63 1969-12-31 16:00:07.623 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -63 1969-12-31 16:00:09.14 -63.0 821UdmGbkEf4j 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -63 1969-12-31 16:00:13.752 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -63 1969-12-31 16:00:14.899 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -63 1969-12-31 16:00:15.827 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 +true -64 1969-12-31 15:59:58.959 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:00.013 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:00.172 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:00.631 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:01.305 -64.0 cvLH6Eat2yFsyy7p 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:01.79 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:02.496 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:03.088 -64.0 cvLH6Eat2yFsyy7p 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:04.662 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:10.273 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:11.952 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 +true -64 1969-12-31 16:00:12.857 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 diff --git ql/src/test/results/clientpositive/parquet_vectorization_14.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_14.q.out similarity index 86% rename from ql/src/test/results/clientpositive/parquet_vectorization_14.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_14.q.out index 9076ecc6c5..84c8bcd195 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_14.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_14.q.out @@ -74,137 +74,147 @@ PLAN VECTORIZATION: STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) (type: boolean) - Statistics: Num rows: 12288 Data size: 1889990 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 14:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 14:float)), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 15:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 15:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp))) - predicate: ((UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) (type: boolean) - Statistics: Num rows: 758 Data size: 116802 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) (type: boolean) + Statistics: Num rows: 12288 Data size: 1889990 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -257), FilterDoubleColLessDoubleColumn(col 4:float, col 14:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 14:float)), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleColumn(col 15:double, col 5:double)(children: CastLongToDouble(col 2:int) -> 15:double), FilterTimestampColLessTimestampColumn(col 9:timestamp, col 8:timestamp))) + predicate: ((UDFToLong(ctinyint) <= cbigint) and (cdouble < UDFToDouble(ctinyint)) and ((cbigint > -257L) or (cfloat < UDFToFloat(cint))) and ((UDFToDouble(cint) <= cdouble) or (ctimestamp2 < ctimestamp1))) (type: boolean) + Statistics: Num rows: 758 Data size: 116802 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [8, 4, 6, 10, 5, 17, 22, 4, 23] + selectExpressions: DoubleColUnaryMinus(col 16:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 19:double, col 21:double)(children: DoubleColUnaryMinus(col 18:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 20:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 20:double) -> 21:double) -> 22:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 23:double + Statistics: Num rows: 758 Data size: 116802 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 22:double) -> double, VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFCount(col 17:double) -> bigint, VectorUDAFMaxDouble(col 4:float) -> float, VectorUDAFSumDouble(col 23:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 6:string, col 4:float, col 5:double, col 8:timestamp, col 10:boolean + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] + keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 379 Data size: 62308 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) + null sort order: zzzzz + sort order: +++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 379 Data size: 62308 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), max(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), count(VALUE._col6) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFCountMerge(col 7:bigint) -> bigint, VectorUDAFMaxDouble(col 8:float) -> float, VectorUDAFSumDouble(col 9:double) -> double, VectorUDAFSumDouble(col 10:double) -> double, VectorUDAFCountMerge(col 11:bigint) -> bigint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:string, col 1:float, col 2:double, col 3:timestamp, col 4:boolean + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] + keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 379 Data size: 62308 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [3, 1, 0, 4, 2, 12, 14, 22, 23, 8, 24, 25, 28, 33, 11, 37, 46, 47, 51, 56, 63, 65] + selectExpressions: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 12:double, DoubleColUnaryMinus(col 13:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 13:double) -> 14:double, FuncPowerDoubleToDouble(col 21:double)(children: DoubleColDivideLongColumn(col 17:double, col 20:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 16:double)(children: DoubleColDivideLongColumn(col 15:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 15:double) -> 16:double) -> 17:double, IfExprNullCondExpr(col 18:boolean, null, col 19:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 18:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 19:bigint) -> 20:bigint) -> 21:double) -> 22:double, DoubleColMultiplyDoubleScalar(col 1:float, val -26.280000686645508) -> 23:float, DoubleColUnaryMinus(col 1:float) -> 24:float, DoubleColUnaryMinus(col 8:float) -> 25:float, DoubleColDivideDoubleScalar(col 27:double, val 10.175)(children: DoubleColUnaryMinus(col 26:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 26:double) -> 27:double) -> 28:double, FuncPowerDoubleToDouble(col 32:double)(children: DoubleColDivideLongColumn(col 31:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 29:double) -> 30:double) -> 31:double) -> 32:double) -> 33:double, DoubleColUnaryMinus(col 36:double)(children: DoubleColDivideDoubleScalar(col 35:double, val 10.175)(children: DoubleColUnaryMinus(col 34:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 2:double) -> 34:double) -> 35:double) -> 36:double) -> 37:double, DoubleScalarModuloDoubleColumn(val -1.389, col 45:double)(children: FuncPowerDoubleToDouble(col 44:double)(children: DoubleColDivideLongColumn(col 40:double, col 43:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 39:double)(children: DoubleColDivideLongColumn(col 38:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 38:double) -> 39:double) -> 40:double, IfExprNullCondExpr(col 41:boolean, null, col 42:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 41:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 42:bigint) -> 43:bigint) -> 44:double) -> 45:double) -> 46:double, DoubleColSubtractDoubleColumn(col 1:double, col 2:double)(children: col 1:float) -> 47:double, DoubleColDivideLongColumn(col 50:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 49:double)(children: DoubleColDivideLongColumn(col 48:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 48:double) -> 49:double) -> 50:double) -> 51:double, DoubleColModuloDoubleScalar(col 55:double, val 10.175)(children: DoubleColDivideLongColumn(col 54:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 53:double)(children: DoubleColDivideLongColumn(col 52:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 52:double) -> 53:double) -> 54:double) -> 55:double) -> 56:double, DoubleColDivideLongColumn(col 59:double, col 62:bigint)(children: DoubleColSubtractDoubleColumn(col 9:double, col 58:double)(children: DoubleColDivideLongColumn(col 57:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 10:double, col 10:double) -> 57:double) -> 58:double) -> 59:double, IfExprNullCondExpr(col 60:boolean, null, col 61:bigint)(children: LongColEqualLongScalar(col 11:bigint, val 1) -> 60:boolean, LongColSubtractLongScalar(col 11:bigint, val 1) -> 61:bigint) -> 62:bigint) -> 63:double, DoubleColUnaryMinus(col 64:double)(children: DoubleColSubtractDoubleColumn(col 1:double, col 2:double)(children: col 1:float) -> 64:double) -> 65:double + Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) + null sort order: zzzz + sort order: ++++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) + Reducer 3 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Select Operator - expressions: ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), cboolean1 (type: boolean), cdouble (type: double), (- (-26.28D + cdouble)) (type: double), ((- (-26.28D + cdouble)) * (- (-26.28D + cdouble))) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [8, 4, 6, 10, 5, 17, 22, 4, 23] - selectExpressions: DoubleColUnaryMinus(col 16:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 16:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 19:double, col 21:double)(children: DoubleColUnaryMinus(col 18:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 18:double) -> 19:double, DoubleColUnaryMinus(col 20:double)(children: DoubleScalarAddDoubleColumn(val -26.28, col 5:double) -> 20:double) -> 21:double) -> 22:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 23:double - Statistics: Num rows: 758 Data size: 116802 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col6), sum(_col5), count(_col5), max(_col1), sum(_col8), sum(_col7), count(_col1) - Group By Vectorization: - aggregators: VectorUDAFSumDouble(col 22:double) -> double, VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFCount(col 17:double) -> bigint, VectorUDAFMaxDouble(col 4:float) -> float, VectorUDAFSumDouble(col 23:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 6:string, col 4:float, col 5:double, col 8:timestamp, col 10:boolean + projectedOutputColumnNums: [3, 1, 0, 4, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21] + Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6] - keys: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp), _col3 (type: boolean) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 379 Data size: 62308 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) - null sort order: zzzzz - sort order: +++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: float), _col2 (type: double), _col3 (type: timestamp), _col4 (type: boolean) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 379 Data size: 62308 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), max(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), count(VALUE._col6) - keys: KEY._col0 (type: string), KEY._col1 (type: float), KEY._col2 (type: double), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 379 Data size: 62308 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col3 (type: timestamp), _col1 (type: float), _col0 (type: string), _col4 (type: boolean), _col2 (type: double), (-26.28D + _col2) (type: double), (- (-26.28D + _col2)) (type: double), power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double), (_col1 * -26.28) (type: float), _col8 (type: float), (- _col1) (type: float), (- _col8) (type: float), ((- (-26.28D + _col2)) / 10.175D) (type: double), power(((_col9 - ((_col10 * _col10) / _col11)) / _col11), 0.5) (type: double), _col11 (type: bigint), (- ((- (-26.28D + _col2)) / 10.175D)) (type: double), (-1.389D % power(((_col5 - ((_col6 * _col6) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5)) (type: double), (UDFToDouble(_col1) - _col2) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / _col11) (type: double), (((_col9 - ((_col10 * _col10) / _col11)) / _col11) % 10.175D) (type: double), ((_col9 - ((_col10 * _col10) / _col11)) / CASE WHEN ((_col11 = 1L)) THEN (null) ELSE ((_col11 - 1)) END) (type: double), (- (UDFToDouble(_col1) - _col2)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - Reduce Output Operator - key expressions: _col2 (type: string), _col1 (type: float), _col4 (type: double), _col0 (type: timestamp) - null sort order: zzzz - sort order: ++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col3 (type: boolean), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: float), _col10 (type: float), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: bigint), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey3 (type: timestamp), KEY.reducesinkkey1 (type: float), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: boolean), KEY.reducesinkkey2 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: float), VALUE._col6 (type: float), VALUE._col7 (type: float), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: bigint), VALUE._col11 (type: double), VALUE._col12 (type: double), VALUE._col13 (type: double), VALUE._col14 (type: double), VALUE._col15 (type: double), VALUE._col16 (type: double), VALUE._col17 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21 - Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 379 Data size: 88080 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_vectorization_15.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_15.q.out similarity index 50% rename from ql/src/test/results/clientpositive/parquet_vectorization_15.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_15.q.out index 2f974b86ad..65921375f6 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_15.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_15.q.out @@ -70,135 +70,119 @@ PLAN VECTORIZATION: STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cstring1 like '10%') or (cstring2 like '%ss%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern 10%), FilterStringColLikeStringScalar(col 7:string, pattern %ss%), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -75), FilterLongColEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -3728.0))) - predicate: ((cstring1 like '10%') or (cstring2 like '%ss%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [4, 10, 5, 6, 0, 2, 8, 4, 13, 14, 17, 18, 21] - selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, CastLongToDouble(col 2:int) -> 18:double, DoubleColMultiplyDoubleColumn(col 19:double, col 20:double)(children: CastLongToDouble(col 2:int) -> 19:double, CastLongToDouble(col 2:int) -> 20:double) -> 21:double - Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col8), sum(_col7), count(_col0), min(_col2), sum(_col10), sum(_col9), count(_col4), sum(_col12), sum(_col11), count(_col5) - Group By Vectorization: - aggregators: VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFMinDouble(col 5:double) -> double, VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFSumDouble(col 14:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFSumDouble(col 21:double) -> double, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFCount(col 2:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 4:float, col 10:boolean, col 5:double, col 6:string, col 0:tinyint, col 2:int, col 8:timestamp - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] - keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 6144 Data size: 1216372 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cstring1 like '10%') or (cstring2 like '%ss%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D))) (type: boolean) + Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern 10%), FilterStringColLikeStringScalar(col 7:string, pattern %ss%), FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2:int, val -75), FilterLongColEqualLongColumn(col 0:smallint, col 1:smallint)(children: col 0:tinyint), FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -3728.0))) + predicate: ((cstring1 like '10%') or (cstring2 like '%ss%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0D))) (type: boolean) + Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [4, 10, 5, 6, 0, 2, 8, 4, 13, 14, 17, 18, 21] + selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 13:double, CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, CastLongToDouble(col 2:int) -> 18:double, DoubleColMultiplyDoubleColumn(col 19:double, col 20:double)(children: CastLongToDouble(col 2:int) -> 19:double, CastLongToDouble(col 2:int) -> 20:double) -> 21:double + Statistics: Num rows: 12288 Data size: 2367002 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col8), sum(_col7), count(_col0), min(_col2), sum(_col10), sum(_col9), count(_col4), sum(_col12), sum(_col11), count(_col5) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFMinDouble(col 5:double) -> double, VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFSumDouble(col 14:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFSumDouble(col 21:double) -> double, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFCount(col 2:int) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 4:float, col 10:boolean, col 5:double, col 6:string, col 0:tinyint, col 2:int, col 8:timestamp + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 + Statistics: Num rows: 6144 Data size: 1216372 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + null sort order: zzzzzzz + sort order: +++++++ + Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 6144 Data size: 1216372 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: llap + Reduce Vectorization: + enabled: false + enableConditionsMet: hive.execution.engine tez IN [tez, spark] IS true + enableConditionsNotMet: hive.vectorized.execution.reduce.enabled IS false + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), min(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), count(VALUE._col6), sum(VALUE._col7), sum(VALUE._col8), count(VALUE._col9) + keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 + Statistics: Num rows: 6144 Data size: 1216372 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), power(((_col7 - ((_col8 * _col8) / _col9)) / CASE WHEN ((_col9 = 1L)) THEN (null) ELSE ((_col9 - 1)) END), 0.5) (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col10 (type: double), (_col2 * 79.553D) (type: double), (33.0 % _col0) (type: float), power(((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END), 0.5) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (-23.0D % _col2) (type: double), (- _col4) (type: tinyint), ((_col14 - ((_col15 * _col15) / _col16)) / CASE WHEN ((_col16 = 1L)) THEN (null) ELSE ((_col16 - 1)) END) (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), power(((_col14 - ((_col15 * _col15) / _col16)) / _col16), 0.5) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) null sort order: zzzzzzz sort order: +++++++ - Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 1216372 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsNotMet: hive.vectorized.execution.reduce.enabled IS false, hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), min(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), count(VALUE._col6), sum(VALUE._col7), sum(VALUE._col8), count(VALUE._col9) - keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 - Statistics: Num rows: 6144 Data size: 1216372 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), power(((_col7 - ((_col8 * _col8) / _col9)) / CASE WHEN ((_col9 = 1L)) THEN (null) ELSE ((_col9 - 1)) END), 0.5) (type: double), (-26.28 - CAST( _col5 AS decimal(10,0))) (type: decimal(13,2)), _col10 (type: double), (_col2 * 79.553D) (type: double), (33.0 % _col0) (type: float), power(((_col11 - ((_col12 * _col12) / _col13)) / CASE WHEN ((_col13 = 1L)) THEN (null) ELSE ((_col13 - 1)) END), 0.5) (type: double), ((_col11 - ((_col12 * _col12) / _col13)) / _col13) (type: double), (-23.0D % _col2) (type: double), (- _col4) (type: tinyint), ((_col14 - ((_col15 * _col15) / _col16)) / CASE WHEN ((_col16 = 1L)) THEN (null) ELSE ((_col16 - 1)) END) (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - CAST( _col5 AS decimal(10,0)))) (type: decimal(13,2)), power(((_col14 - ((_col15 * _col15) / _col16)) / _col16), 0.5) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - Reduce Output Operator - key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) - null sort order: zzzzzzz - sort order: +++++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsNotMet: hive.vectorized.execution.reduce.enabled IS false, hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col7 (type: double), _col8 (type: decimal(13,2)), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: tinyint), _col16 (type: double), _col17 (type: float), _col18 (type: int), _col19 (type: decimal(13,2)), _col20 (type: double) + Reducer 3 + Execution mode: llap + Reduce Vectorization: + enabled: false + enableConditionsMet: hive.execution.engine tez IN [tez, spark] IS true + enableConditionsNotMet: hive.vectorized.execution.reduce.enabled IS false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: float), KEY.reducesinkkey1 (type: boolean), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: tinyint), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: timestamp), VALUE._col0 (type: double), VALUE._col1 (type: decimal(13,2)), VALUE._col2 (type: double), VALUE._col3 (type: double), VALUE._col4 (type: float), VALUE._col5 (type: double), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: tinyint), VALUE._col9 (type: double), VALUE._col10 (type: float), VALUE._col11 (type: int), VALUE._col12 (type: decimal(13,2)), VALUE._col13 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 6144 Data size: 2592628 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_vectorization_16.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_16.q.out similarity index 84% rename from ql/src/test/results/clientpositive/parquet_vectorization_16.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_16.q.out index da42363e45..e547554170 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_16.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_16.q.out @@ -52,89 +52,115 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2183514 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) - predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [6, 5, 8, 13] - selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) - Group By Vectorization: - aggregators: VectorUDAFCount(col 5:double) -> bigint, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFMinDouble(col 5:double) -> double - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 6:string, col 5:double, col 8:timestamp - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3] - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) + Statistics: Num rows: 12288 Data size: 2183514 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) + predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) + Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [6, 5, 8, 13] + selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double + Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) + Group By Vectorization: + aggregators: VectorUDAFCount(col 5:double) -> bigint, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFMinDouble(col 5:double) -> double + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 6:string, col 5:double, col 8:timestamp + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3] + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), min(VALUE._col3) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFMinDouble(col 6:double) -> double + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:string, col 1:double, col 2:timestamp + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0, 1, 2, 3] + keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 7, 9, 3, 17, 26, 36, 6, 37, 39, 47] + selectExpressions: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 7:double, DoubleColUnaryMinus(col 8:double)(children: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 8:double) -> 9:double, FuncPowerDoubleToDouble(col 16:double)(children: DoubleColDivideLongColumn(col 12:double, col 15:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 11:double) -> 12:double, IfExprNullCondExpr(col 13:boolean, null, col 14:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 14:bigint) -> 15:bigint) -> 16:double) -> 17:double, DoubleColUnaryMinus(col 25:double)(children: FuncPowerDoubleToDouble(col 24:double)(children: DoubleColDivideLongColumn(col 20:double, col 23:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 19:double)(children: DoubleColDivideLongColumn(col 18:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 18:double) -> 19:double) -> 20:double, IfExprNullCondExpr(col 21:boolean, null, col 22:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 21:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 22:bigint) -> 23:bigint) -> 24:double) -> 25:double) -> 26:double, DoubleColMultiplyDoubleColumn(col 34:double, col 35:double)(children: FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 29:double, col 32:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 27:double) -> 28:double) -> 29:double, IfExprNullCondExpr(col 30:boolean, null, col 31:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 30:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 31:bigint) -> 32:bigint) -> 33:double) -> 34:double, CastLongToDouble(col 3:bigint) -> 35:double) -> 36:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 1:double) -> 37:double, DecimalColDivideDecimalScalar(col 38:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 38:decimal(19,0)) -> 39:decimal(28,6), FuncPowerDoubleToDouble(col 46:double)(children: DoubleColDivideLongColumn(col 42:double, col 45:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 41:double)(children: DoubleColDivideLongColumn(col 40:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 40:double) -> 41:double) -> 42:double, IfExprNullCondExpr(col 43:boolean, null, col 44:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 43:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 44:bigint) -> 45:bigint) -> 46:double) -> 47:double + Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), min(VALUE._col3) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_vectorization_17.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_17.q.out similarity index 86% rename from ql/src/test/results/clientpositive/parquet_vectorization_17.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_17.q.out index 8f0d2d8546..541126a492 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_17.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_17.q.out @@ -60,67 +60,84 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cbigint > -23L) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257))) (type: boolean) - Statistics: Num rows: 12288 Data size: 1522990 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float)), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimal64ColGreaterDecimal64Scalar(col 13:decimal(13,3)/DECIMAL_64, val -863257)(children: CastLongToDecimal64(col 2:int) -> 13:decimal(13,3)/DECIMAL_64))) - predicate: ((cbigint > -23L) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257))) (type: boolean) - Statistics: Num rows: 6141 Data size: 761216 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cbigint > -23L) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257))) (type: boolean) + Statistics: Num rows: 12288 Data size: 1522990 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val -23), FilterExprOrExpr(children: FilterLongColGreaterEqualLongScalar(col 0:tinyint, val 33), FilterLongColGreaterEqualLongColumn(col 1:bigint, col 3:bigint)(children: col 1:smallint), FilterDoubleColEqualDoubleColumn(col 4:double, col 5:double)(children: col 4:float)), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 5:double, val 988888.0), FilterDecimal64ColGreaterDecimal64Scalar(col 13:decimal(13,3)/DECIMAL_64, val -863257)(children: CastLongToDecimal64(col 2:int) -> 13:decimal(13,3)/DECIMAL_64))) + predicate: ((cbigint > -23L) and ((ctinyint >= 33Y) or (UDFToLong(csmallint) >= cbigint) or (UDFToDouble(cfloat) = cdouble)) and ((cdouble <> 988888.0D) or (CAST( cint AS decimal(13,3)) > -863.257))) (type: boolean) + Statistics: Num rows: 6141 Data size: 761216 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 17, 20, 22, 24, 26, 29] + selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 17:double, DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 18:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 18:double) -> 19:double) -> 20:double, DoubleColDivideDoubleColumn(col 5:double, col 21:double)(children: CastLongToDouble(col 2:int) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 23:double)(children: DoubleColUnaryMinus(col 5:double) -> 23:double) -> 24:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 25:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 25:decimal(19,0)) -> 26:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 28:double)(children: DoubleColUnaryMinus(col 27:double)(children: DoubleColUnaryMinus(col 5:double) -> 27:double) -> 28:double) -> 29:double + Statistics: Num rows: 6141 Data size: 1756220 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col5 (type: bigint), _col0 (type: float) + null sort order: zz + sort order: ++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 6141 Data size: 1756220 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Select Operator - expressions: cfloat (type: float), cstring1 (type: string), cint (type: int), ctimestamp1 (type: timestamp), cdouble (type: double), cbigint (type: bigint), (UDFToDouble(cfloat) / UDFToDouble(ctinyint)) (type: double), (UDFToLong(cint) % cbigint) (type: bigint), (- cdouble) (type: double), (cdouble + (UDFToDouble(cfloat) / UDFToDouble(ctinyint))) (type: double), (cdouble / UDFToDouble(cint)) (type: double), (- (- cdouble)) (type: double), (9763215.5639 % CAST( cbigint AS decimal(19,0))) (type: decimal(11,4)), (2563.58D + (- (- cdouble))) (type: double) + expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [4, 6, 2, 8, 5, 3, 15, 16, 17, 20, 22, 24, 26, 29] - selectExpressions: DoubleColDivideDoubleColumn(col 4:double, col 14:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 14:double) -> 15:double, LongColModuloLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int) -> 16:bigint, DoubleColUnaryMinus(col 5:double) -> 17:double, DoubleColAddDoubleColumn(col 5:double, col 19:double)(children: DoubleColDivideDoubleColumn(col 4:double, col 18:double)(children: col 4:float, CastLongToDouble(col 0:tinyint) -> 18:double) -> 19:double) -> 20:double, DoubleColDivideDoubleColumn(col 5:double, col 21:double)(children: CastLongToDouble(col 2:int) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 23:double)(children: DoubleColUnaryMinus(col 5:double) -> 23:double) -> 24:double, DecimalScalarModuloDecimalColumn(val 9763215.5639, col 25:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 25:decimal(19,0)) -> 26:decimal(11,4), DoubleScalarAddDoubleColumn(val 2563.58, col 28:double)(children: DoubleColUnaryMinus(col 27:double)(children: DoubleColUnaryMinus(col 5:double) -> 27:double) -> 28:double) -> 29:double + projectedOutputColumnNums: [1, 2, 3, 4, 5, 0, 6, 7, 8, 9, 10, 11, 12, 13] Statistics: Num rows: 6141 Data size: 1756220 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col5 (type: bigint), _col0 (type: float) - null sort order: zz - sort order: ++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 6141 Data size: 1756220 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: timestamp), _col4 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: decimal(11,4)), _col13 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: float), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: timestamp), VALUE._col3 (type: double), KEY.reducesinkkey0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: bigint), VALUE._col6 (type: double), VALUE._col7 (type: double), VALUE._col8 (type: double), VALUE._col9 (type: double), VALUE._col10 (type: decimal(11,4)), VALUE._col11 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 6141 Data size: 1756220 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6141 Data size: 1756220 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_2.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_2.q.out new file mode 100644 index 0000000000..0633a15e0b --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_2.q.out @@ -0,0 +1,219 @@ +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT AVG(csmallint), + (AVG(csmallint) % -563), + (AVG(csmallint) + 762), + SUM(cfloat), + VAR_POP(cbigint), + (-(VAR_POP(cbigint))), + (SUM(cfloat) - AVG(csmallint)), + COUNT(*), + (-((SUM(cfloat) - AVG(csmallint)))), + (VAR_POP(cbigint) - 762), + MIN(ctinyint), + ((-(VAR_POP(cbigint))) + MIN(ctinyint)), + AVG(cdouble), + (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) +FROM alltypesparquet +WHERE (((ctimestamp1 < ctimestamp2) + AND ((cstring2 LIKE 'b%') + AND (cfloat <= -5638.15))) + OR ((cdouble < ctinyint) + AND ((-10669 != ctimestamp2) + OR (359 > cint)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT AVG(csmallint), + (AVG(csmallint) % -563), + (AVG(csmallint) + 762), + SUM(cfloat), + VAR_POP(cbigint), + (-(VAR_POP(cbigint))), + (SUM(cfloat) - AVG(csmallint)), + COUNT(*), + (-((SUM(cfloat) - AVG(csmallint)))), + (VAR_POP(cbigint) - 762), + MIN(ctinyint), + ((-(VAR_POP(cbigint))) + MIN(ctinyint)), + AVG(cdouble), + (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) +FROM alltypesparquet +WHERE (((ctimestamp1 < ctimestamp2) + AND ((cstring2 LIKE 'b%') + AND (cfloat <= -5638.15))) + OR ((cdouble < ctinyint) + AND ((-10669 != ctimestamp2) + OR (359 > cint)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean) + Statistics: Num rows: 12288 Data size: 1908244 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 14:double, val -10669.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterLongColLessLongScalar(col 2:int, val 359))), FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8:timestamp, col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern b%), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -5638.14990234375))) + predicate: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean) + Statistics: Num rows: 4096 Data size: 636272 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: csmallint (type: smallint), cfloat (type: float), cbigint (type: bigint), ctinyint (type: tinyint), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 4, 3, 0, 5, 15, 18] + selectExpressions: CastLongToDouble(col 3:bigint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 3:bigint) -> 16:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 18:double + Statistics: Num rows: 4096 Data size: 636272 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count(), min(_col3), sum(_col4), count(_col4) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 1:smallint) -> bigint, VectorUDAFCount(col 1:smallint) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 15:double) -> double, VectorUDAFCount(col 3:bigint) -> bigint, VectorUDAFCountStar(*) -> bigint, VectorUDAFMinLong(col 0:tinyint) -> tinyint, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), count(VALUE._col6), min(VALUE._col7), sum(VALUE._col8), count(VALUE._col9) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint, VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFSumDouble(col 2:double) -> double, VectorUDAFSumDouble(col 3:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCountMerge(col 5:bigint) -> bigint, VectorUDAFCountMerge(col 6:bigint) -> bigint, VectorUDAFMinLong(col 7:tinyint) -> tinyint, VectorUDAFSumDouble(col 8:double) -> double, VectorUDAFCountMerge(col 9:bigint) -> bigint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + native: false + vectorProcessingMode: GLOBAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToDouble(_col0) / _col1) (type: double), ((UDFToDouble(_col0) / _col1) % -563.0D) (type: double), ((UDFToDouble(_col0) / _col1) + 762.0D) (type: double), _col2 (type: double), ((_col3 - ((_col4 * _col4) / _col5)) / _col5) (type: double), (- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) (type: double), (_col2 - (UDFToDouble(_col0) / _col1)) (type: double), _col6 (type: bigint), (- (_col2 - (UDFToDouble(_col0) / _col1))) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / _col5) - 762.0D) (type: double), _col7 (type: tinyint), ((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) (type: double), (_col8 / _col9) (type: double), (((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) - _col2) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [11, 14, 17, 2, 21, 26, 29, 6, 33, 38, 7, 45, 46, 54] + selectExpressions: DoubleColDivideLongColumn(col 10:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 10:double) -> 11:double, DoubleColModuloDoubleScalar(col 13:double, val -563.0)(children: DoubleColDivideLongColumn(col 12:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 12:double) -> 13:double) -> 14:double, DoubleColAddDoubleScalar(col 16:double, val 762.0)(children: DoubleColDivideLongColumn(col 15:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 15:double) -> 16:double) -> 17:double, DoubleColDivideLongColumn(col 20:double, col 5:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 19:double)(children: DoubleColDivideLongColumn(col 18:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 18:double) -> 19:double) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 25:double)(children: DoubleColDivideLongColumn(col 24:double, col 5:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 22:double) -> 23:double) -> 24:double) -> 25:double) -> 26:double, DoubleColSubtractDoubleColumn(col 2:double, col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 27:double) -> 28:double) -> 29:double, DoubleColUnaryMinus(col 32:double)(children: DoubleColSubtractDoubleColumn(col 2:double, col 31:double)(children: DoubleColDivideLongColumn(col 30:double, col 1:bigint)(children: CastLongToDouble(col 0:bigint) -> 30:double) -> 31:double) -> 32:double) -> 33:double, DoubleColSubtractDoubleScalar(col 37:double, val 762.0)(children: DoubleColDivideLongColumn(col 36:double, col 5:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 35:double)(children: DoubleColDivideLongColumn(col 34:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 34:double) -> 35:double) -> 36:double) -> 37:double) -> 38:double, DoubleColAddDoubleColumn(col 43:double, col 44:double)(children: DoubleColUnaryMinus(col 42:double)(children: DoubleColDivideLongColumn(col 41:double, col 5:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 40:double)(children: DoubleColDivideLongColumn(col 39:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 39:double) -> 40:double) -> 41:double) -> 42:double) -> 43:double, CastLongToDouble(col 7:tinyint) -> 44:double) -> 45:double, DoubleColDivideLongColumn(col 8:double, col 9:bigint) -> 46:double, DoubleColSubtractDoubleColumn(col 53:double, col 2:double)(children: DoubleColAddDoubleColumn(col 51:double, col 52:double)(children: DoubleColUnaryMinus(col 50:double)(children: DoubleColDivideLongColumn(col 49:double, col 5:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 48:double)(children: DoubleColDivideLongColumn(col 47:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 47:double) -> 48:double) -> 49:double) -> 50:double) -> 51:double, CastLongToDouble(col 7:tinyint) -> 52:double) -> 53:double) -> 54:double + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT AVG(csmallint), + (AVG(csmallint) % -563), + (AVG(csmallint) + 762), + SUM(cfloat), + VAR_POP(cbigint), + (-(VAR_POP(cbigint))), + (SUM(cfloat) - AVG(csmallint)), + COUNT(*), + (-((SUM(cfloat) - AVG(csmallint)))), + (VAR_POP(cbigint) - 762), + MIN(ctinyint), + ((-(VAR_POP(cbigint))) + MIN(ctinyint)), + AVG(cdouble), + (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) +FROM alltypesparquet +WHERE (((ctimestamp1 < ctimestamp2) + AND ((cstring2 LIKE 'b%') + AND (cfloat <= -5638.15))) + OR ((cdouble < ctinyint) + AND ((-10669 != ctimestamp2) + OR (359 > cint)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT AVG(csmallint), + (AVG(csmallint) % -563), + (AVG(csmallint) + 762), + SUM(cfloat), + VAR_POP(cbigint), + (-(VAR_POP(cbigint))), + (SUM(cfloat) - AVG(csmallint)), + COUNT(*), + (-((SUM(cfloat) - AVG(csmallint)))), + (VAR_POP(cbigint) - 762), + MIN(ctinyint), + ((-(VAR_POP(cbigint))) + MIN(ctinyint)), + AVG(cdouble), + (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) +FROM alltypesparquet +WHERE (((ctimestamp1 < ctimestamp2) + AND ((cstring2 LIKE 'b%') + AND (cfloat <= -5638.15))) + OR ((cdouble < ctinyint) + AND ((-10669 != ctimestamp2) + OR (359 > cint)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-5646.467075892857 -16.467075892856883 -4884.467075892857 -2839.634998679161 1.49936299222378906E18 -1.49936299222378906E18 2806.832077213696 3584 -2806.832077213696 1.49936299222378829E18 -64 -1.49936299222378906E18 -5650.1297631138395 -1.49936299222378624E18 diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_3.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_3.q.out new file mode 100644 index 0000000000..f81172c012 --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_3.q.out @@ -0,0 +1,229 @@ +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT STDDEV_SAMP(csmallint), + (STDDEV_SAMP(csmallint) - 10.175), + STDDEV_POP(ctinyint), + (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), + (-(STDDEV_POP(ctinyint))), + (STDDEV_SAMP(csmallint) % 79.553), + (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), + STDDEV_SAMP(cfloat), + (-(STDDEV_SAMP(csmallint))), + SUM(cfloat), + ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), + (-((STDDEV_SAMP(csmallint) - 10.175))), + AVG(cint), + (-3728 - STDDEV_SAMP(csmallint)), + STDDEV_POP(cint), + (AVG(cint) / STDDEV_SAMP(cfloat)) +FROM alltypesparquet +WHERE (((cint <= cfloat) + AND ((79.553 != cbigint) + AND (ctimestamp2 = -29071))) + OR ((cbigint > cdouble) + AND ((79.553 <= csmallint) + AND (ctimestamp1 > ctimestamp2)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT STDDEV_SAMP(csmallint), + (STDDEV_SAMP(csmallint) - 10.175), + STDDEV_POP(ctinyint), + (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), + (-(STDDEV_POP(ctinyint))), + (STDDEV_SAMP(csmallint) % 79.553), + (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), + STDDEV_SAMP(cfloat), + (-(STDDEV_SAMP(csmallint))), + SUM(cfloat), + ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), + (-((STDDEV_SAMP(csmallint) - 10.175))), + AVG(cint), + (-3728 - STDDEV_SAMP(csmallint)), + STDDEV_POP(cint), + (AVG(cint) / STDDEV_SAMP(cfloat)) +FROM alltypesparquet +WHERE (((cint <= cfloat) + AND ((79.553 != cbigint) + AND (ctimestamp2 = -29071))) + OR ((cbigint > cdouble) + AND ((79.553 <= csmallint) + AND (ctimestamp1 > ctimestamp2)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D)) or ((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2))) (type: boolean) + Statistics: Num rows: 12288 Data size: 1027540 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float), FilterDecimalColNotEqualDecimalScalar(col 14:decimal(22,3), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterDoubleColEqualDoubleScalar(col 15:double, val -29071.0)(children: CastTimestampToDouble(col 9:timestamp) -> 15:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 16:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 16:double), FilterDecimal64ColGreaterEqualDecimal64Scalar(col 17:decimal(8,3)/DECIMAL_64, val 79553)(children: CastLongToDecimal64(col 1:smallint) -> 17:decimal(8,3)/DECIMAL_64), FilterTimestampColGreaterTimestampColumn(col 8:timestamp, col 9:timestamp))) + predicate: (((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D)) or ((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2))) (type: boolean) + Statistics: Num rows: 2503 Data size: 209380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cint (type: int), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0, 4, 2, 18, 21, 22, 25, 4, 26, 27, 30] + selectExpressions: CastLongToDouble(col 1:smallint) -> 18:double, DoubleColMultiplyDoubleColumn(col 19:double, col 20:double)(children: CastLongToDouble(col 1:smallint) -> 19:double, CastLongToDouble(col 1:smallint) -> 20:double) -> 21:double, CastLongToDouble(col 0:tinyint) -> 22:double, DoubleColMultiplyDoubleColumn(col 23:double, col 24:double)(children: CastLongToDouble(col 0:tinyint) -> 23:double, CastLongToDouble(col 0:tinyint) -> 24:double) -> 25:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 26:double, CastLongToDouble(col 2:int) -> 27:double, DoubleColMultiplyDoubleColumn(col 28:double, col 29:double)(children: CastLongToDouble(col 2:int) -> 28:double, CastLongToDouble(col 2:int) -> 29:double) -> 30:double + Statistics: Num rows: 2503 Data size: 209380 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col7), sum(_col6), count(_col1), sum(_col9), sum(_col8), count(_col2), sum(_col2), sum(_col3), count(_col3), sum(_col11), sum(_col10) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 21:double) -> double, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFCount(col 1:smallint) -> bigint, VectorUDAFSumDouble(col 25:double) -> double, VectorUDAFSumDouble(col 22:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFSumDouble(col 26:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFCount(col 2:int) -> bigint, VectorUDAFSumDouble(col 30:double) -> double, VectorUDAFSumDouble(col 27:double) -> double + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: double), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: double), _col13 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), sum(VALUE._col9), sum(VALUE._col10), count(VALUE._col11), sum(VALUE._col12), sum(VALUE._col13) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 0:double) -> double, VectorUDAFSumDouble(col 1:double) -> double, VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFSumDouble(col 3:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCountMerge(col 5:bigint) -> bigint, VectorUDAFSumDouble(col 6:double) -> double, VectorUDAFSumDouble(col 7:double) -> double, VectorUDAFCountMerge(col 8:bigint) -> bigint, VectorUDAFSumDouble(col 9:double) -> double, VectorUDAFSumLong(col 10:bigint) -> bigint, VectorUDAFCountMerge(col 11:bigint) -> bigint, VectorUDAFSumDouble(col 12:double) -> double, VectorUDAFSumDouble(col 13:double) -> double + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + native: false + vectorProcessingMode: GLOBAL + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D) (type: double), power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5)) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) % 79.553D) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) (type: double), power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5) (type: double), (- power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), _col9 (type: double), ((- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) / (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (UDFToDouble(_col10) / _col11) (type: double), (-3728.0D - power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), power(((_col12 - ((_col13 * _col13) / _col11)) / _col11), 0.5) (type: double), ((UDFToDouble(_col10) / _col11) / power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [21, 30, 35, 53, 59, 68, 87, 95, 104, 9, 133, 143, 145, 154, 159, 170] + selectExpressions: FuncPowerDoubleToDouble(col 20:double)(children: DoubleColDivideLongColumn(col 16:double, col 19:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 14:double) -> 15:double) -> 16:double, IfExprNullCondExpr(col 17:boolean, null, col 18:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 17:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 18:bigint) -> 19:bigint) -> 20:double) -> 21:double, DoubleColSubtractDoubleScalar(col 29:double, val 10.175)(children: FuncPowerDoubleToDouble(col 28:double)(children: DoubleColDivideLongColumn(col 24:double, col 27:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 22:double) -> 23:double) -> 24:double, IfExprNullCondExpr(col 25:boolean, null, col 26:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 25:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 26:bigint) -> 27:bigint) -> 28:double) -> 29:double) -> 30:double, FuncPowerDoubleToDouble(col 34:double)(children: DoubleColDivideLongColumn(col 33:double, col 5:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 32:double)(children: DoubleColDivideLongColumn(col 31:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 31:double) -> 32:double) -> 33:double) -> 34:double) -> 35:double, DoubleColMultiplyDoubleColumn(col 43:double, col 52:double)(children: FuncPowerDoubleToDouble(col 42:double)(children: DoubleColDivideLongColumn(col 38:double, col 41:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 37:double)(children: DoubleColDivideLongColumn(col 36:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 36:double) -> 37:double) -> 38:double, IfExprNullCondExpr(col 39:boolean, null, col 40:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 39:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 40:bigint) -> 41:bigint) -> 42:double) -> 43:double, DoubleColSubtractDoubleScalar(col 51:double, val 10.175)(children: FuncPowerDoubleToDouble(col 50:double)(children: DoubleColDivideLongColumn(col 46:double, col 49:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 45:double)(children: DoubleColDivideLongColumn(col 44:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 44:double) -> 45:double) -> 46:double, IfExprNullCondExpr(col 47:boolean, null, col 48:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 47:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 48:bigint) -> 49:bigint) -> 50:double) -> 51:double) -> 52:double) -> 53:double, DoubleColUnaryMinus(col 58:double)(children: FuncPowerDoubleToDouble(col 57:double)(children: DoubleColDivideLongColumn(col 56:double, col 5:bigint)(children: DoubleColSubtractDoubleColumn(col 3:double, col 55:double)(children: DoubleColDivideLongColumn(col 54:double, col 5:bigint)(children: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double) -> 54:double) -> 55:double) -> 56:double) -> 57:double) -> 58:double) -> 59:double, DoubleColModuloDoubleScalar(col 67:double, val 79.553)(children: FuncPowerDoubleToDouble(col 66:double)(children: DoubleColDivideLongColumn(col 62:double, col 65:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 61:double)(children: DoubleColDivideLongColumn(col 60:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 60:double) -> 61:double) -> 62:double, IfExprNullCondExpr(col 63:boolean, null, col 64:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 63:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 64:bigint) -> 65:bigint) -> 66:double) -> 67:double) -> 68:double, DoubleColUnaryMinus(col 86:double)(children: DoubleColMultiplyDoubleColumn(col 76:double, col 85:double)(children: FuncPowerDoubleToDouble(col 75:double)(children: DoubleColDivideLongColumn(col 71:double, col 74:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 70:double)(children: DoubleColDivideLongColumn(col 69:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 69:double) -> 70:double) -> 71:double, IfExprNullCondExpr(col 72:boolean, null, col 73:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 72:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 73:bigint) -> 74:bigint) -> 75:double) -> 76:double, DoubleColSubtractDoubleScalar(col 84:double, val 10.175)(children: FuncPowerDoubleToDouble(col 83:double)(children: DoubleColDivideLongColumn(col 79:double, col 82:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 78:double)(children: DoubleColDivideLongColumn(col 77:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 77:double) -> 78:double) -> 79:double, IfExprNullCondExpr(col 80:boolean, null, col 81:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 80:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 81:bigint) -> 82:bigint) -> 83:double) -> 84:double) -> 85:double) -> 86:double) -> 87:double, FuncPowerDoubleToDouble(col 94:double)(children: DoubleColDivideLongColumn(col 90:double, col 93:bigint)(children: DoubleColSubtractDoubleColumn(col 6:double, col 89:double)(children: DoubleColDivideLongColumn(col 88:double, col 8:bigint)(children: DoubleColMultiplyDoubleColumn(col 7:double, col 7:double) -> 88:double) -> 89:double) -> 90:double, IfExprNullCondExpr(col 91:boolean, null, col 92:bigint)(children: LongColEqualLongScalar(col 8:bigint, val 1) -> 91:boolean, LongColSubtractLongScalar(col 8:bigint, val 1) -> 92:bigint) -> 93:bigint) -> 94:double) -> 95:double, DoubleColUnaryMinus(col 103:double)(children: FuncPowerDoubleToDouble(col 102:double)(children: DoubleColDivideLongColumn(col 98:double, col 101:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 97:double)(children: DoubleColDivideLongColumn(col 96:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 96:double) -> 97:double) -> 98:double, IfExprNullCondExpr(col 99:boolean, null, col 100:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 99:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 100:bigint) -> 101:bigint) -> 102:double) -> 103:double) -> 104:double, DoubleColDivideDoubleColumn(col 123:double, col 132:double)(children: DoubleColUnaryMinus(col 122:double)(children: DoubleColMultiplyDoubleColumn(col 112:double, col 121:double)(children: FuncPowerDoubleToDouble(col 111:double)(children: DoubleColDivideLongColumn(col 107:double, col 110:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 106:double)(children: DoubleColDivideLongColumn(col 105:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 105:double) -> 106:double) -> 107:double, IfExprNullCondExpr(col 108:boolean, null, col 109:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 108:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 109:bigint) -> 110:bigint) -> 111:double) -> 112:double, DoubleColSubtractDoubleScalar(col 120:double, val 10.175)(children: FuncPowerDoubleToDouble(col 119:double)(children: DoubleColDivideLongColumn(col 115:double, col 118:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 114:double)(children: DoubleColDivideLongColumn(col 113:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 113:double) -> 114:double) -> 115:double, IfExprNullCondExpr(col 116:boolean, null, col 117:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 116:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 117:bigint) -> 118:bigint) -> 119:double) -> 120:double) -> 121:double) -> 122:double) -> 123:double, DoubleColSubtractDoubleScalar(col 131:double, val 10.175)(children: FuncPowerDoubleToDouble(col 130:double)(children: DoubleColDivideLongColumn(col 126:double, col 129:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 125:double)(children: DoubleColDivideLongColumn(col 124:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 124:double) -> 125:double) -> 126:double, IfExprNullCondExpr(col 127:boolean, null, col 128:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 127:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 128:bigint) -> 129:bigint) -> 130:double) -> 131:double) -> 132:double) -> 133:double, DoubleColUnaryMinus(col 142:double)(children: DoubleColSubtractDoubleScalar(col 141:double, val 10.175)(children: FuncPowerDoubleToDouble(col 140:double)(children: DoubleColDivideLongColumn(col 136:double, col 139:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 135:double)(children: DoubleColDivideLongColumn(col 134:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 134:double) -> 135:double) -> 136:double, IfExprNullCondExpr(col 137:boolean, null, col 138:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 137:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 138:bigint) -> 139:bigint) -> 140:double) -> 141:double) -> 142:double) -> 143:double, DoubleColDivideLongColumn(col 144:double, col 11:bigint)(children: CastLongToDouble(col 10:bigint) -> 144:double) -> 145:double, DoubleScalarSubtractDoubleColumn(val -3728.0, col 153:double)(children: FuncPowerDoubleToDouble(col 152:double)(children: DoubleColDivideLongColumn(col 148:double, col 151:bigint)(children: DoubleColSubtractDoubleColumn(col 0:double, col 147:double)(children: DoubleColDivideLongColumn(col 146:double, col 2:bigint)(children: DoubleColMultiplyDoubleColumn(col 1:double, col 1:double) -> 146:double) -> 147:double) -> 148:double, IfExprNullCondExpr(col 149:boolean, null, col 150:bigint)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 149:boolean, LongColSubtractLongScalar(col 2:bigint, val 1) -> 150:bigint) -> 151:bigint) -> 152:double) -> 153:double) -> 154:double, FuncPowerDoubleToDouble(col 158:double)(children: DoubleColDivideLongColumn(col 157:double, col 11:bigint)(children: DoubleColSubtractDoubleColumn(col 12:double, col 156:double)(children: DoubleColDivideLongColumn(col 155:double, col 11:bigint)(children: DoubleColMultiplyDoubleColumn(col 13:double, col 13:double) -> 155:double) -> 156:double) -> 157:double) -> 158:double) -> 159:double, DoubleColDivideDoubleColumn(col 161:double, col 169:double)(children: DoubleColDivideLongColumn(col 160:double, col 11:bigint)(children: CastLongToDouble(col 10:bigint) -> 160:double) -> 161:double, FuncPowerDoubleToDouble(col 168:double)(children: DoubleColDivideLongColumn(col 164:double, col 167:bigint)(children: DoubleColSubtractDoubleColumn(col 6:double, col 163:double)(children: DoubleColDivideLongColumn(col 162:double, col 8:bigint)(children: DoubleColMultiplyDoubleColumn(col 7:double, col 7:double) -> 162:double) -> 163:double) -> 164:double, IfExprNullCondExpr(col 165:boolean, null, col 166:bigint)(children: LongColEqualLongScalar(col 8:bigint, val 1) -> 165:boolean, LongColSubtractLongScalar(col 8:bigint, val 1) -> 166:bigint) -> 167:bigint) -> 168:double) -> 169:double) -> 170:double + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: SELECT STDDEV_SAMP(csmallint), + (STDDEV_SAMP(csmallint) - 10.175), + STDDEV_POP(ctinyint), + (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), + (-(STDDEV_POP(ctinyint))), + (STDDEV_SAMP(csmallint) % 79.553), + (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), + STDDEV_SAMP(cfloat), + (-(STDDEV_SAMP(csmallint))), + SUM(cfloat), + ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), + (-((STDDEV_SAMP(csmallint) - 10.175))), + AVG(cint), + (-3728 - STDDEV_SAMP(csmallint)), + STDDEV_POP(cint), + (AVG(cint) / STDDEV_SAMP(cfloat)) +FROM alltypesparquet +WHERE (((cint <= cfloat) + AND ((79.553 != cbigint) + AND (ctimestamp2 = -29071))) + OR ((cbigint > cdouble) + AND ((79.553 <= csmallint) + AND (ctimestamp1 > ctimestamp2)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT STDDEV_SAMP(csmallint), + (STDDEV_SAMP(csmallint) - 10.175), + STDDEV_POP(ctinyint), + (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), + (-(STDDEV_POP(ctinyint))), + (STDDEV_SAMP(csmallint) % 79.553), + (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), + STDDEV_SAMP(cfloat), + (-(STDDEV_SAMP(csmallint))), + SUM(cfloat), + ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), + (-((STDDEV_SAMP(csmallint) - 10.175))), + AVG(cint), + (-3728 - STDDEV_SAMP(csmallint)), + STDDEV_POP(cint), + (AVG(cint) / STDDEV_SAMP(cfloat)) +FROM alltypesparquet +WHERE (((cint <= cfloat) + AND ((79.553 != cbigint) + AND (ctimestamp2 = -29071))) + OR ((cbigint > cdouble) + AND ((79.553 <= csmallint) + AND (ctimestamp1 > ctimestamp2)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +0.0 -10.175 34.287285216637066 -0.0 -34.287285216637066 0.0 0.0 34.3469009551564 -0.0 197.89499950408936 -0.0 10.175 NULL -3728.0 NULL NULL diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_4.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_4.q.out new file mode 100644 index 0000000000..7cacbde9bf --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_4.q.out @@ -0,0 +1,219 @@ +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT SUM(cint), + (SUM(cint) * -563), + (-3728 + SUM(cint)), + STDDEV_POP(cdouble), + (-(STDDEV_POP(cdouble))), + AVG(cdouble), + ((SUM(cint) * -563) % SUM(cint)), + (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), + VAR_POP(cdouble), + (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), + ((-3728 + SUM(cint)) - (SUM(cint) * -563)), + MIN(ctinyint), + MIN(ctinyint), + (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) +FROM alltypesparquet +WHERE (((csmallint >= cint) + OR ((-89010 >= ctinyint) + AND (cdouble > 79.553))) + OR ((-563 != cbigint) + AND ((ctinyint != cbigint) + OR (-3728 >= cdouble)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT SUM(cint), + (SUM(cint) * -563), + (-3728 + SUM(cint)), + STDDEV_POP(cdouble), + (-(STDDEV_POP(cdouble))), + AVG(cdouble), + ((SUM(cint) * -563) % SUM(cint)), + (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), + VAR_POP(cdouble), + (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), + ((-3728 + SUM(cint)) - (SUM(cint) * -563)), + MIN(ctinyint), + MIN(ctinyint), + (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) +FROM alltypesparquet +WHERE (((csmallint >= cint) + OR ((-89010 >= ctinyint) + AND (cdouble > 79.553))) + OR ((-563 != cbigint) + AND ((ctinyint != cbigint) + OR (-3728 >= cdouble)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((UDFToInteger(csmallint) >= cint) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or ((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D))) (type: boolean) + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 3:bigint, val -563), FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessEqualDoubleScalar(col 5:double, val -3728.0))), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterDoubleColGreaterDoubleScalar(col 5:double, val 79.553))) + predicate: ((UDFToInteger(csmallint) >= cint) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or ((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D))) (type: boolean) + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int), cdouble (type: double), ctinyint (type: tinyint), (cdouble * cdouble) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [2, 5, 0, 13] + selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double + Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col3), sum(_col1), count(_col1), min(_col2) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint, VectorUDAFMinLong(col 0:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: tinyint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), min(VALUE._col4) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint, VectorUDAFSumDouble(col 1:double) -> double, VectorUDAFSumDouble(col 2:double) -> double, VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFMinLong(col 4:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + native: false + vectorProcessingMode: GLOBAL + projectedOutputColumnNums: [0, 1, 2, 3, 4] + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: bigint), (_col0 * -563L) (type: bigint), (-3728L + _col0) (type: bigint), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (- power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5)) (type: double), (_col2 / _col3) (type: double), ((_col0 * -563L) % _col0) (type: bigint), (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)) (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3))) (type: double), ((-3728L + _col0) - (_col0 * -563L)) (type: bigint), _col4 (type: tinyint), _col4 (type: tinyint), (UDFToDouble(_col4) * (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)))) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5, 6, 11, 17, 18, 20, 25, 29, 35, 38, 4, 4, 46] + selectExpressions: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 5:bigint, LongScalarAddLongColumn(val -3728, col 0:bigint) -> 6:bigint, FuncPowerDoubleToDouble(col 10:double)(children: DoubleColDivideLongColumn(col 9:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 8:double)(children: DoubleColDivideLongColumn(col 7:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 7:double) -> 8:double) -> 9:double) -> 10:double) -> 11:double, DoubleColUnaryMinus(col 16:double)(children: FuncPowerDoubleToDouble(col 15:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 13:double)(children: DoubleColDivideLongColumn(col 12:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 12:double) -> 13:double) -> 14:double) -> 15:double) -> 16:double) -> 17:double, DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 18:double, LongColModuloLongColumn(col 19:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 19:bigint) -> 20:bigint, DoubleColDivideDoubleColumn(col 23:double, col 24:double)(children: CastLongToDouble(col 22:bigint)(children: LongColModuloLongColumn(col 21:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 21:bigint) -> 22:bigint) -> 23:double, DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 24:double) -> 25:double, DoubleColDivideLongColumn(col 28:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 27:double)(children: DoubleColDivideLongColumn(col 26:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 26:double) -> 27:double) -> 28:double) -> 29:double, DoubleColUnaryMinus(col 34:double)(children: DoubleColDivideDoubleColumn(col 32:double, col 33:double)(children: CastLongToDouble(col 31:bigint)(children: LongColModuloLongColumn(col 30:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 30:bigint) -> 31:bigint) -> 32:double, DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 33:double) -> 34:double) -> 35:double, LongColSubtractLongColumn(col 36:bigint, col 37:bigint)(children: LongScalarAddLongColumn(val -3728, col 0:bigint) -> 36:bigint, LongColMultiplyLongScalar(col 0:bigint, val -563) -> 37:bigint) -> 38:bigint, DoubleColMultiplyDoubleColumn(col 39:double, col 45:double)(children: CastLongToDouble(col 4:tinyint) -> 39:double, DoubleColUnaryMinus(col 44:double)(children: DoubleColDivideDoubleColumn(col 42:double, col 43:double)(children: CastLongToDouble(col 41:bigint)(children: LongColModuloLongColumn(col 40:bigint, col 0:bigint)(children: LongColMultiplyLongScalar(col 0:bigint, val -563) -> 40:bigint) -> 41:bigint) -> 42:double, DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 43:double) -> 44:double) -> 45:double) -> 46:double + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(cint), + (SUM(cint) * -563), + (-3728 + SUM(cint)), + STDDEV_POP(cdouble), + (-(STDDEV_POP(cdouble))), + AVG(cdouble), + ((SUM(cint) * -563) % SUM(cint)), + (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), + VAR_POP(cdouble), + (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), + ((-3728 + SUM(cint)) - (SUM(cint) * -563)), + MIN(ctinyint), + MIN(ctinyint), + (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) +FROM alltypesparquet +WHERE (((csmallint >= cint) + OR ((-89010 >= ctinyint) + AND (cdouble > 79.553))) + OR ((-563 != cbigint) + AND ((ctinyint != cbigint) + OR (-3728 >= cdouble)))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(cint), + (SUM(cint) * -563), + (-3728 + SUM(cint)), + STDDEV_POP(cdouble), + (-(STDDEV_POP(cdouble))), + AVG(cdouble), + ((SUM(cint) * -563) % SUM(cint)), + (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), + VAR_POP(cdouble), + (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), + ((-3728 + SUM(cint)) - (SUM(cint) * -563)), + MIN(ctinyint), + MIN(ctinyint), + (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) +FROM alltypesparquet +WHERE (((csmallint >= cint) + OR ((-89010 >= ctinyint) + AND (cdouble > 79.553))) + OR ((-563 != cbigint) + AND ((ctinyint != cbigint) + OR (-3728 >= cdouble)))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-493101012745 277615870175435 -493101016473 136727.78682963562 -136727.78682963562 2298.5515807767374 0 0.0 1.8694487691330276E10 -0.0 -278108971191908 -64 -64 0.0 diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_5.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_5.q.out new file mode 100644 index 0000000000..36b17d7081 --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_5.q.out @@ -0,0 +1,206 @@ +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT MAX(csmallint), + (MAX(csmallint) * -75), + COUNT(*), + ((MAX(csmallint) * -75) / COUNT(*)), + (6981 * MAX(csmallint)), + MIN(csmallint), + (-(MIN(csmallint))), + (197 % ((MAX(csmallint) * -75) / COUNT(*))), + SUM(cint), + MAX(ctinyint), + (-(MAX(ctinyint))), + ((-(MAX(ctinyint))) + MAX(ctinyint)) +FROM alltypesparquet +WHERE (((cboolean2 IS NOT NULL) + AND (cstring1 LIKE '%b%')) + OR ((ctinyint = cdouble) + AND ((ctimestamp2 IS NOT NULL) + AND (cstring2 LIKE 'a')))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT MAX(csmallint), + (MAX(csmallint) * -75), + COUNT(*), + ((MAX(csmallint) * -75) / COUNT(*)), + (6981 * MAX(csmallint)), + MIN(csmallint), + (-(MIN(csmallint))), + (197 % ((MAX(csmallint) * -75) / COUNT(*))), + SUM(cint), + MAX(ctinyint), + (-(MAX(ctinyint))), + ((-(MAX(ctinyint))) + MAX(ctinyint)) +FROM alltypesparquet +WHERE (((cboolean2 IS NOT NULL) + AND (cstring1 LIKE '%b%')) + OR ((ctinyint = cdouble) + AND ((ctimestamp2 IS NOT NULL) + AND (cstring2 LIKE 'a')))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cstring1 like '%b%') and cboolean2 is not null) or ((UDFToDouble(ctinyint) = cdouble) and (cstring2 like 'a') and ctimestamp2 is not null)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2330342 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %b%), SelectColumnIsNotNull(col 11:boolean)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterStringColLikeStringScalar(col 7:string, pattern a), SelectColumnIsNotNull(col 9:timestamp))) + predicate: (((cstring1 like '%b%') and cboolean2 is not null) or ((UDFToDouble(ctinyint) = cdouble) and (cstring2 like 'a') and ctimestamp2 is not null)) (type: boolean) + Statistics: Num rows: 6879 Data size: 1304690 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) + outputColumnNames: ctinyint, csmallint, cint + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2] + Statistics: Num rows: 6879 Data size: 1304690 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 1:smallint) -> smallint, VectorUDAFCountStar(*) -> bigint, VectorUDAFMinLong(col 1:smallint) -> smallint, VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFMaxLong(col 0:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: HASH + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3, 4] + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: tinyint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0), count(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), max(VALUE._col4) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 0:smallint) -> smallint, VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFMinLong(col 2:smallint) -> smallint, VectorUDAFSumLong(col 3:bigint) -> bigint, VectorUDAFMaxLong(col 4:tinyint) -> tinyint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + native: false + vectorProcessingMode: GLOBAL + projectedOutputColumnNums: [0, 1, 2, 3, 4] + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: smallint), (UDFToInteger(_col0) * -75) (type: int), _col1 (type: bigint), (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1)) (type: double), (6981 * UDFToInteger(_col0)) (type: int), _col2 (type: smallint), (- _col2) (type: smallint), (197.0D % (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1))) (type: double), _col3 (type: bigint), _col4 (type: tinyint), (- _col4) (type: tinyint), ((- _col4) + _col4) (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5, 1, 9, 10, 2, 11, 16, 3, 4, 17, 19] + selectExpressions: LongColMultiplyLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 5:int, DoubleColDivideDoubleColumn(col 7:double, col 8:double)(children: CastLongToDouble(col 6:int)(children: LongColMultiplyLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 6:int) -> 7:double, CastLongToDouble(col 1:bigint) -> 8:double) -> 9:double, LongScalarMultiplyLongColumn(val 6981, col 0:int)(children: col 0:smallint) -> 10:int, LongColUnaryMinus(col 2:smallint) -> 11:smallint, DoubleScalarModuloDoubleColumn(val 197.0, col 15:double)(children: DoubleColDivideDoubleColumn(col 13:double, col 14:double)(children: CastLongToDouble(col 12:int)(children: LongColMultiplyLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 12:int) -> 13:double, CastLongToDouble(col 1:bigint) -> 14:double) -> 15:double) -> 16:double, LongColUnaryMinus(col 4:tinyint) -> 17:tinyint, LongColAddLongColumn(col 18:tinyint, col 4:tinyint)(children: LongColUnaryMinus(col 4:tinyint) -> 18:tinyint) -> 19:tinyint + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT MAX(csmallint), + (MAX(csmallint) * -75), + COUNT(*), + ((MAX(csmallint) * -75) / COUNT(*)), + (6981 * MAX(csmallint)), + MIN(csmallint), + (-(MIN(csmallint))), + (197 % ((MAX(csmallint) * -75) / COUNT(*))), + SUM(cint), + MAX(ctinyint), + (-(MAX(ctinyint))), + ((-(MAX(ctinyint))) + MAX(ctinyint)) +FROM alltypesparquet +WHERE (((cboolean2 IS NOT NULL) + AND (cstring1 LIKE '%b%')) + OR ((ctinyint = cdouble) + AND ((ctimestamp2 IS NOT NULL) + AND (cstring2 LIKE 'a')))) +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT MAX(csmallint), + (MAX(csmallint) * -75), + COUNT(*), + ((MAX(csmallint) * -75) / COUNT(*)), + (6981 * MAX(csmallint)), + MIN(csmallint), + (-(MIN(csmallint))), + (197 % ((MAX(csmallint) * -75) / COUNT(*))), + SUM(cint), + MAX(ctinyint), + (-(MAX(ctinyint))), + ((-(MAX(ctinyint))) + MAX(ctinyint)) +FROM alltypesparquet +WHERE (((cboolean2 IS NOT NULL) + AND (cstring1 LIKE '%b%')) + OR ((ctinyint = cdouble) + AND ((ctimestamp2 IS NOT NULL) + AND (cstring2 LIKE 'a')))) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +16343 -1225725 1070 -1145.53738317757 114090483 -16307 16307 197.0 -26853917571 11 -11 0 diff --git ql/src/test/results/clientpositive/parquet_vectorization_6.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_6.q.out similarity index 96% rename from ql/src/test/results/clientpositive/parquet_vectorization_6.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_6.q.out index 59dad74855..7a3c59e9ac 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_6.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_6.q.out @@ -54,50 +54,54 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (((cstring2 like '%a') or (cfloat <= -257.0)) and cbigint is not null)) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2110130 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10:boolean, val 0), FilterLongColGreaterEqualLongColumn(col 11:boolean, col 10:boolean)), FilterExprAndExpr(children: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %a), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -257.0)), SelectColumnIsNotNull(col 3:bigint))), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) - predicate: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (((cstring2 like '%a') or (cfloat <= -257.0)) and cbigint is not null)) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 5951 Data size: 1022000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28D / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [10, 4, 6, 13, 14, 15, 16, 17, 18, 19, 20, 22] - selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1:int)(children: col 1:smallint) -> 13:int, LongColUnaryMinus(col 1:smallint) -> 14:smallint, DoubleColUnaryMinus(col 4:float) -> 15:float, DoubleScalarDivideDoubleColumn(val -26.28, col 4:double)(children: col 4:float) -> 16:double, DoubleColMultiplyDoubleScalar(col 4:float, val 359.0) -> 17:float, LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 18:int, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColSubtractLongScalar(col 0:int, val -75)(children: col 0:tinyint) -> 20:int, LongScalarMultiplyLongColumn(val 762, col 21:int)(children: LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 21:int) -> 22:int - Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (((cstring2 like '%a') or (cfloat <= -257.0)) and cbigint is not null)) and (ctinyint <> 0Y)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2110130 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 10:boolean, val 0), FilterLongColGreaterEqualLongColumn(col 11:boolean, col 10:boolean)), FilterExprAndExpr(children: FilterExprOrExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %a), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -257.0)), SelectColumnIsNotNull(col 3:bigint))), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) + predicate: ((((cboolean1 <= 0) and (cboolean2 >= cboolean1)) or (((cstring2 like '%a') or (cfloat <= -257.0)) and cbigint is not null)) and (ctinyint <> 0Y)) (type: boolean) + Statistics: Num rows: 5951 Data size: 1022000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cboolean1 (type: boolean), cfloat (type: float), cstring1 (type: string), (988888 * UDFToInteger(csmallint)) (type: int), (- csmallint) (type: smallint), (- cfloat) (type: float), (-26.28D / UDFToDouble(cfloat)) (type: double), (cfloat * 359.0) (type: float), (cint % UDFToInteger(ctinyint)) (type: int), (- cdouble) (type: double), (UDFToInteger(ctinyint) - -75) (type: int), (762 * (cint % UDFToInteger(ctinyint))) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [10, 4, 6, 13, 14, 15, 16, 17, 18, 19, 20, 22] + selectExpressions: LongScalarMultiplyLongColumn(val 988888, col 1:int)(children: col 1:smallint) -> 13:int, LongColUnaryMinus(col 1:smallint) -> 14:smallint, DoubleColUnaryMinus(col 4:float) -> 15:float, DoubleScalarDivideDoubleColumn(val -26.28, col 4:double)(children: col 4:float) -> 16:double, DoubleColMultiplyDoubleScalar(col 4:float, val 359.0) -> 17:float, LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 18:int, DoubleColUnaryMinus(col 5:double) -> 19:double, LongColSubtractLongScalar(col 0:int, val -75)(children: col 0:tinyint) -> 20:int, LongScalarMultiplyLongColumn(val 762, col 21:int)(children: LongColModuloLongColumn(col 2:int, col 0:int)(children: col 0:tinyint) -> 21:int) -> 22:int + Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 5951 Data size: 715128 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_7.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_7.q.out new file mode 100644 index 0000000000..58b6ba7f8f --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_7.q.out @@ -0,0 +1,500 @@ +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28815) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28815) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2770698 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28815.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) + predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) + Statistics: Num rows: 11033 Data size: 2487724 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: +++++++++++++++ + keys: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + null sort order: zzzzzzzzzzzzzzz + Statistics: Num rows: 11033 Data size: 2487724 Basic stats: COMPLETE Column stats: COMPLETE + top n: 25 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 10:boolean, col 3:bigint, col 1:smallint, col 0:tinyint, col 8:timestamp, col 6:string, LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint + native: true + Select Operator + expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 19, 21, 25, 27, 29, 31, 32, 33, 35] + selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 19:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 21:int, LongColUnaryMinus(col 1:smallint) -> 25:smallint, LongColUnaryMinus(col 0:tinyint) -> 27:tinyint, LongColAddLongScalar(col 28:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 28:tinyint) -> 29:int, LongColMultiplyLongColumn(col 3:bigint, col 30:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 30:smallint) -> 31:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 32:int, LongColUnaryMinus(col 0:tinyint) -> 33:tinyint, LongColModuloLongColumn(col 34:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 34:tinyint) -> 35:tinyint + Statistics: Num rows: 11033 Data size: 1323416 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) + null sort order: zzzzzzzzzzzzzzz + sort order: +++++++++++++++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 11033 Data size: 1323416 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 9, 14] + Statistics: Num rows: 11033 Data size: 1323416 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 25 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 25 Data size: 3102 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 25 Data size: 3102 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 25 + Processor Tree: + ListSink + +PREHOOK: query: SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28815) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28815) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +true NULL -15892 29 1969-12-31 15:59:57.937 821UdmGbkEf4j NULL -215 15892 -29 -12 NULL 171 -29 0 +true NULL -15899 50 1969-12-31 15:59:46.926 821UdmGbkEf4j NULL -222 15899 -50 -33 NULL 10210 -50 0 +true NULL -15903 -2 1969-12-31 15:59:46.371 cvLH6Eat2yFsyy7p NULL -226 15903 2 19 NULL 14465 2 0 +true NULL -15920 -64 1969-12-31 15:59:51.859 cvLH6Eat2yFsyy7p NULL -243 15920 64 81 NULL 6687 64 0 +true NULL -15922 -17 1969-12-31 15:59:46.164 821UdmGbkEf4j NULL -245 15922 17 34 NULL 10851 17 0 +true NULL -15923 49 1969-12-31 15:59:47.323 cvLH6Eat2yFsyy7p NULL -246 15923 -49 -32 NULL 2628 -49 0 +true NULL -15935 -6 1969-12-31 15:59:45.859 1cGVWH7n1QU NULL -1 15935 6 23 NULL 12046 6 0 +true NULL -15948 31 1969-12-31 15:59:47.577 821UdmGbkEf4j NULL -14 15948 -31 -14 NULL 7799 -31 0 +true NULL -15948 6 1969-12-31 15:59:49.269 1cGVWH7n1QU NULL -14 15948 -6 11 NULL 12436 -6 0 +true NULL -15980 -6 1969-12-31 15:59:54.84 1cGVWH7n1QU NULL -46 15980 6 23 NULL 14836 6 0 +true NULL -15999 4 1969-12-31 15:59:46.491 1cGVWH7n1QU NULL -65 15999 -4 13 NULL 1231 -4 0 +true NULL -16017 -21 1969-12-31 15:59:44.02 821UdmGbkEf4j NULL -83 16017 21 38 NULL 2282 21 0 +true NULL -16025 -42 1969-12-31 15:59:54.534 cvLH6Eat2yFsyy7p NULL -91 16025 42 59 NULL 14242 42 0 +true NULL -16036 -15 1969-12-31 15:59:58.681 1cGVWH7n1QU NULL -102 16036 15 32 NULL 7928 15 0 +true NULL -16059 -35 1969-12-31 15:59:53.038 821UdmGbkEf4j NULL -125 16059 35 52 NULL 12437 35 0 +true NULL -16076 59 1969-12-31 15:59:55.023 821UdmGbkEf4j NULL -142 16076 -59 -42 NULL 7907 -59 0 +true NULL -16122 50 1969-12-31 15:59:51.608 1cGVWH7n1QU NULL -188 16122 -50 -33 NULL 1828 -50 0 +true NULL -16123 -20 1969-12-31 15:59:51.177 1cGVWH7n1QU NULL -189 16123 20 37 NULL 2217 20 0 +true NULL -16153 35 1969-12-31 15:59:52.036 1cGVWH7n1QU NULL -219 16153 -35 -18 NULL 14817 -35 0 +true NULL -16169 5 1969-12-31 15:59:45.059 1cGVWH7n1QU NULL -235 16169 -5 12 NULL 6104 -5 0 +true NULL -16207 -4 1969-12-31 15:59:45.956 cvLH6Eat2yFsyy7p NULL -16 16207 4 21 NULL 8290 4 0 +true NULL -16221 -12 1969-12-31 15:59:45.877 1cGVWH7n1QU NULL -30 16221 12 29 NULL 1378 12 0 +true NULL -16227 2 1969-12-31 15:59:44.065 821UdmGbkEf4j NULL -36 16227 -2 15 NULL 9761 -2 0 +true NULL -16305 3 1969-12-31 15:59:43.878 1cGVWH7n1QU NULL -114 16305 -3 14 NULL 8491 -3 0 +true NULL -16339 15 1969-12-31 15:59:53.966 821UdmGbkEf4j NULL -148 16339 -15 2 NULL 12588 -15 0 +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800.0) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28792.3149999999999995) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800.0) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28792.3149999999999995) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2770698 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28792.315)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) + predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) + Statistics: Num rows: 11033 Data size: 2487724 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: +++++++++++++++ + keys: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + null sort order: zzzzzzzzzzzzzzz + Statistics: Num rows: 11033 Data size: 2487724 Basic stats: COMPLETE Column stats: COMPLETE + top n: 25 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 10:boolean, col 3:bigint, col 1:smallint, col 0:tinyint, col 8:timestamp, col 6:string, LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint + native: true + Select Operator + expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 19, 21, 25, 27, 29, 31, 32, 33, 35] + selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 19:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 21:int, LongColUnaryMinus(col 1:smallint) -> 25:smallint, LongColUnaryMinus(col 0:tinyint) -> 27:tinyint, LongColAddLongScalar(col 28:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 28:tinyint) -> 29:int, LongColMultiplyLongColumn(col 3:bigint, col 30:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 30:smallint) -> 31:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 32:int, LongColUnaryMinus(col 0:tinyint) -> 33:tinyint, LongColModuloLongColumn(col 34:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 34:tinyint) -> 35:tinyint + Statistics: Num rows: 11033 Data size: 1323416 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) + null sort order: zzzzzzzzzzzzzzz + sort order: +++++++++++++++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 11033 Data size: 1323416 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 9, 14] + Statistics: Num rows: 11033 Data size: 1323416 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 25 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 25 Data size: 3102 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 25 Data size: 3102 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 25 + Processor Tree: + ListSink + +PREHOOK: query: SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800.0) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28792.3149999999999995) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT cboolean1, + cbigint, + csmallint, + ctinyint, + ctimestamp1, + cstring1, + (cbigint + cbigint) as c1, + (csmallint % -257) as c2, + (-(csmallint)) as c3, + (-(ctinyint)) as c4, + ((-(ctinyint)) + 17) as c5, + (cbigint * (-(csmallint))) as c6, + (cint % csmallint) as c7, + (-(ctinyint)) as c8, + ((-(ctinyint)) % ctinyint) as c9 +FROM alltypesparquet +WHERE ((ctinyint != 0) + AND (((ctimestamp1 <= -28800.0) + OR ((ctinyint = cint) + OR (cstring2 LIKE 'ss'))) + AND ((988888 < cdouble) + OR ((ctimestamp2 > -28792.3149999999999995) + AND (3569 >= cdouble))))) +ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +true NULL -14584 -7 1969-12-31 15:59:46.965 1cGVWH7n1QU NULL -192 14584 7 24 NULL 5864 7 0 +true NULL -14739 4 1969-12-31 15:59:55.188 cvLH6Eat2yFsyy7p NULL -90 14739 -4 13 NULL 8966 -4 0 +true NULL -14771 13 1969-12-31 15:59:58.839 821UdmGbkEf4j NULL -122 14771 -13 4 NULL 12897 -13 0 +true NULL -15149 20 1969-12-31 15:59:46.575 1cGVWH7n1QU NULL -243 15149 -20 -3 NULL 10520 -20 0 +true NULL -15344 48 1969-12-31 15:59:54.853 821UdmGbkEf4j NULL -181 15344 -48 -31 NULL 13871 -48 0 +true NULL -15388 49 1969-12-31 15:59:58.545 cvLH6Eat2yFsyy7p NULL -225 15388 -49 -32 NULL 3131 -49 0 +true NULL -15431 -11 1969-12-31 15:59:52.176 cvLH6Eat2yFsyy7p NULL -11 15431 11 28 NULL 7586 11 0 +true NULL -15435 -21 1969-12-31 15:59:54.705 1cGVWH7n1QU NULL -15 15435 21 38 NULL 6586 21 0 +true NULL -15450 -34 1969-12-31 15:59:55.681 cvLH6Eat2yFsyy7p NULL -30 15450 34 51 NULL 5717 34 0 +true NULL -15478 7 1969-12-31 15:59:56.809 cvLH6Eat2yFsyy7p NULL -58 15478 -7 10 NULL 7501 -7 0 +true NULL -15555 -2 1969-12-31 15:59:58.773 1cGVWH7n1QU NULL -135 15555 2 19 NULL 9991 2 0 +true NULL -15659 -11 1969-12-31 15:59:48.466 cvLH6Eat2yFsyy7p NULL -239 15659 11 28 NULL 12199 11 0 +true NULL -15711 -60 1969-12-31 15:59:53.115 821UdmGbkEf4j NULL -34 15711 60 77 NULL 7646 60 0 +true NULL -15770 -23 1969-12-31 15:59:56.822 1cGVWH7n1QU NULL -93 15770 23 40 NULL 4926 23 0 +true NULL -15794 53 1969-12-31 15:59:53.749 cvLH6Eat2yFsyy7p NULL -117 15794 -53 -36 NULL 4351 -53 0 +true NULL -15892 29 1969-12-31 15:59:57.937 821UdmGbkEf4j NULL -215 15892 -29 -12 NULL 171 -29 0 +true NULL -15899 50 1969-12-31 15:59:46.926 821UdmGbkEf4j NULL -222 15899 -50 -33 NULL 10210 -50 0 +true NULL -15920 -64 1969-12-31 15:59:51.859 cvLH6Eat2yFsyy7p NULL -243 15920 64 81 NULL 6687 64 0 +true NULL -15922 -17 1969-12-31 15:59:46.164 821UdmGbkEf4j NULL -245 15922 17 34 NULL 10851 17 0 +true NULL -15980 -6 1969-12-31 15:59:54.84 1cGVWH7n1QU NULL -46 15980 6 23 NULL 14836 6 0 +true NULL -16017 -21 1969-12-31 15:59:44.02 821UdmGbkEf4j NULL -83 16017 21 38 NULL 2282 21 0 +true NULL -16036 -15 1969-12-31 15:59:58.681 1cGVWH7n1QU NULL -102 16036 15 32 NULL 7928 15 0 +true NULL -16076 59 1969-12-31 15:59:55.023 821UdmGbkEf4j NULL -142 16076 -59 -42 NULL 7907 -59 0 +true NULL -16122 50 1969-12-31 15:59:51.608 1cGVWH7n1QU NULL -188 16122 -50 -33 NULL 1828 -50 0 +true NULL -16153 35 1969-12-31 15:59:52.036 1cGVWH7n1QU NULL -219 16153 -35 -18 NULL 14817 -35 0 diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_8.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_8.q.out new file mode 100644 index 0000000000..51da3cbf02 --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_8.q.out @@ -0,0 +1,474 @@ +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 10) + AND (ctimestamp2 != 16))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 10) + AND (ctimestamp2 != 16))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2733998 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 10.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val 16.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), SelectColumnIsNotNull(col 7:string)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0), SelectColumnIsNotNull(col 10:boolean))) + predicate: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) + Statistics: Num rows: 3059 Data size: 680930 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++++++++++++++ + keys: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) + null sort order: zzzzzzzzzzzzzz + Statistics: Num rows: 3059 Data size: 680930 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 8:timestamp, col 5:double, col 10:boolean, col 6:string, col 4:float, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 16:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 17:double, DoubleColAddDoubleColumn(col 18:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 18:float) -> 19:float, DoubleColAddDoubleColumn(col 20:double, col 21:double)(children: DoubleColUnaryMinus(col 5:double) -> 20:double, CastLongToDouble(col 3:bigint) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 5:double) -> 23:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 24:float, DoubleColUnaryMinus(col 4:float) -> 25:float, DoubleColAddDoubleColumn(col 26:double, col 28:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 26:double, DoubleColAddDoubleColumn(col 27:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 27:float) -> 28:float) -> 29:double + native: true + Select Operator + expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 18, 21, 27, 20, 26, 28, 33] + selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 18:double, DoubleColAddDoubleColumn(col 20:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 20:float) -> 21:float, DoubleColAddDoubleColumn(col 20:double, col 26:double)(children: DoubleColUnaryMinus(col 5:double) -> 20:double, CastLongToDouble(col 3:bigint) -> 26:double) -> 27:double, DoubleColUnaryMinus(col 5:double) -> 20:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 26:float, DoubleColUnaryMinus(col 4:float) -> 28:float, DoubleColAddDoubleColumn(col 30:double, col 32:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 30:double, DoubleColAddDoubleColumn(col 31:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 31:float) -> 32:float) -> 33:double + Statistics: Num rows: 3059 Data size: 410040 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) + null sort order: zzzzzzzzzzzzzz + sort order: ++++++++++++++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 3059 Data size: 410040 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 5, 11, 12, 13] + Statistics: Num rows: 3059 Data size: 410040 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 20 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 2850 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 2850 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 10) + AND (ctimestamp2 != 16))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 10) + AND (ctimestamp2 != 16))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +1969-12-31 15:59:30.929 -200.0 NULL NULL 12.0 200.0 -5438.15 51400.0 NULL 2.128824065E9 200.0 -13.389 -12.0 NULL +1969-12-31 15:59:30.929 -200.0 NULL NULL 42.0 200.0 -5438.15 51400.0 NULL -5.78935585E8 200.0 -43.389 -42.0 NULL +1969-12-31 15:59:30.929 -7196.0 NULL NULL 49.0 7196.0 1557.8500000000004 1849372.0 NULL 1.948230809E9 7196.0 -50.389 -49.0 NULL +1969-12-31 15:59:30.929 15601.0 NULL NULL -54.0 -15601.0 -21239.15 -4009457.0 NULL -1.114185408E9 -15601.0 52.611 54.0 NULL +1969-12-31 15:59:43.628 -200.0 NULL NULL 23.0 200.0 -5438.15 51400.0 NULL 2.034056161E9 200.0 -24.389 -23.0 NULL +1969-12-31 15:59:43.637 -7196.0 NULL NULL -44.0 7196.0 1557.8500000000004 1849372.0 NULL 1.100301451E9 7196.0 42.611 44.0 NULL +1969-12-31 15:59:43.64 -7196.0 NULL NULL -51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.339157623E9 7196.0 49.611 51.0 NULL +1969-12-31 15:59:43.661 -200.0 NULL NULL 13.0 200.0 -5438.15 51400.0 NULL -6.8063459E7 200.0 -14.389 -13.0 NULL +1969-12-31 15:59:43.676 -200.0 NULL NULL -10.0 200.0 -5438.15 51400.0 NULL 8.34296111E8 200.0 8.611 10.0 NULL +1969-12-31 15:59:43.705 15601.0 NULL NULL -12.0 -15601.0 -21239.15 -4009457.0 NULL 5.95398978E8 -15601.0 10.611 12.0 NULL +1969-12-31 15:59:43.709 15601.0 NULL NULL 61.0 -15601.0 -21239.15 -4009457.0 NULL -1.55652257E8 -15601.0 -62.389 -61.0 NULL +1969-12-31 15:59:43.72 -200.0 NULL NULL -18.0 200.0 -5438.15 51400.0 NULL 1.809037075E9 200.0 16.611 18.0 NULL +1969-12-31 15:59:43.721 15601.0 NULL NULL 57.0 -15601.0 -21239.15 -4009457.0 NULL -1.465672807E9 -15601.0 -58.389 -57.0 NULL +1969-12-31 15:59:43.749 -7196.0 NULL NULL -39.0 7196.0 1557.8500000000004 1849372.0 NULL 3.96436076E8 7196.0 37.611 39.0 NULL +1969-12-31 15:59:43.771 15601.0 NULL NULL 49.0 -15601.0 -21239.15 -4009457.0 NULL -1.10733693E9 -15601.0 -50.389 -49.0 NULL +1969-12-31 15:59:43.773 -200.0 NULL NULL -24.0 200.0 -5438.15 51400.0 NULL -1.046049502E9 200.0 22.611 24.0 NULL +1969-12-31 15:59:43.782 -7196.0 NULL NULL 51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.607339819E9 7196.0 -52.389 -51.0 NULL +1969-12-31 15:59:43.783 -200.0 NULL NULL -11.0 200.0 -5438.15 51400.0 NULL 1.2116287E7 200.0 9.611 11.0 NULL +1969-12-31 15:59:43.807 -7196.0 NULL NULL 42.0 7196.0 1557.8500000000004 1849372.0 NULL -5.98226333E8 7196.0 -43.389 -42.0 NULL +1969-12-31 15:59:43.82 -7196.0 NULL NULL -30.0 7196.0 1557.8500000000004 1849372.0 NULL 1.329550715E9 7196.0 28.611 30.0 NULL +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 12.503) + AND (ctimestamp2 != 11.998))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION +SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 12.503) + AND (ctimestamp2 != 11.998))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) + Statistics: Num rows: 12288 Data size: 2733998 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 12.503)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val 11.998)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), SelectColumnIsNotNull(col 7:string)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0), SelectColumnIsNotNull(col 10:boolean))) + predicate: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) + Statistics: Num rows: 3059 Data size: 680930 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++++++++++++++ + keys: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) + null sort order: zzzzzzzzzzzzzz + Statistics: Num rows: 3059 Data size: 680930 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 8:timestamp, col 5:double, col 10:boolean, col 6:string, col 4:float, DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 16:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 17:double, DoubleColAddDoubleColumn(col 18:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 18:float) -> 19:float, DoubleColAddDoubleColumn(col 20:double, col 21:double)(children: DoubleColUnaryMinus(col 5:double) -> 20:double, CastLongToDouble(col 3:bigint) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 5:double) -> 23:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 24:float, DoubleColUnaryMinus(col 4:float) -> 25:float, DoubleColAddDoubleColumn(col 26:double, col 28:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 26:double, DoubleColAddDoubleColumn(col 27:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 27:float) -> 28:float) -> 29:double + native: true + Select Operator + expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [8, 5, 10, 6, 4, 13, 14, 18, 21, 27, 20, 26, 28, 33] + selectExpressions: DoubleColUnaryMinus(col 5:double) -> 13:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 14:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 18:double, DoubleColAddDoubleColumn(col 20:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 20:float) -> 21:float, DoubleColAddDoubleColumn(col 20:double, col 26:double)(children: DoubleColUnaryMinus(col 5:double) -> 20:double, CastLongToDouble(col 3:bigint) -> 26:double) -> 27:double, DoubleColUnaryMinus(col 5:double) -> 20:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 26:float, DoubleColUnaryMinus(col 4:float) -> 28:float, DoubleColAddDoubleColumn(col 30:double, col 32:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 30:double, DoubleColAddDoubleColumn(col 31:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 31:float) -> 32:float) -> 33:double + Statistics: Num rows: 3059 Data size: 410040 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) + null sort order: zzzzzzzzzzzzzz + sort order: ++++++++++++++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 3059 Data size: 410040 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 5, 11, 12, 13] + Statistics: Num rows: 3059 Data size: 410040 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 20 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 2850 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 2850 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 12.503) + AND (ctimestamp2 != 11.998))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT ctimestamp1, + cdouble, + cboolean1, + cstring1, + cfloat, + (-(cdouble)) as c1, + (-5638.15 - cdouble) as c2, + (cdouble * -257) as c3, + (cint + cfloat) as c4, + ((-(cdouble)) + cbigint) as c5, + (-(cdouble)) as c6, + (-1.389 - cfloat) as c7, + (-(cfloat)) as c8, + ((-5638.15 - cdouble) + (cint + cfloat)) as c9 +FROM alltypesparquet +WHERE (((cstring2 IS NOT NULL) + AND ((ctimestamp1 <= 12.503) + AND (ctimestamp2 != 11.998))) + OR ((cfloat < -6432) + OR ((cboolean1 IS NOT NULL) + AND (cdouble = 988888)))) +ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 +LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +1969-12-31 15:59:30.929 -200.0 NULL NULL 12.0 200.0 -5438.15 51400.0 NULL 2.128824065E9 200.0 -13.389 -12.0 NULL +1969-12-31 15:59:30.929 -200.0 NULL NULL 42.0 200.0 -5438.15 51400.0 NULL -5.78935585E8 200.0 -43.389 -42.0 NULL +1969-12-31 15:59:30.929 -7196.0 NULL NULL 49.0 7196.0 1557.8500000000004 1849372.0 NULL 1.948230809E9 7196.0 -50.389 -49.0 NULL +1969-12-31 15:59:30.929 15601.0 NULL NULL -54.0 -15601.0 -21239.15 -4009457.0 NULL -1.114185408E9 -15601.0 52.611 54.0 NULL +1969-12-31 15:59:43.628 -200.0 NULL NULL 23.0 200.0 -5438.15 51400.0 NULL 2.034056161E9 200.0 -24.389 -23.0 NULL +1969-12-31 15:59:43.637 -7196.0 NULL NULL -44.0 7196.0 1557.8500000000004 1849372.0 NULL 1.100301451E9 7196.0 42.611 44.0 NULL +1969-12-31 15:59:43.64 -7196.0 NULL NULL -51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.339157623E9 7196.0 49.611 51.0 NULL +1969-12-31 15:59:43.661 -200.0 NULL NULL 13.0 200.0 -5438.15 51400.0 NULL -6.8063459E7 200.0 -14.389 -13.0 NULL +1969-12-31 15:59:43.676 -200.0 NULL NULL -10.0 200.0 -5438.15 51400.0 NULL 8.34296111E8 200.0 8.611 10.0 NULL +1969-12-31 15:59:43.705 15601.0 NULL NULL -12.0 -15601.0 -21239.15 -4009457.0 NULL 5.95398978E8 -15601.0 10.611 12.0 NULL +1969-12-31 15:59:43.709 15601.0 NULL NULL 61.0 -15601.0 -21239.15 -4009457.0 NULL -1.55652257E8 -15601.0 -62.389 -61.0 NULL +1969-12-31 15:59:43.72 -200.0 NULL NULL -18.0 200.0 -5438.15 51400.0 NULL 1.809037075E9 200.0 16.611 18.0 NULL +1969-12-31 15:59:43.721 15601.0 NULL NULL 57.0 -15601.0 -21239.15 -4009457.0 NULL -1.465672807E9 -15601.0 -58.389 -57.0 NULL +1969-12-31 15:59:43.749 -7196.0 NULL NULL -39.0 7196.0 1557.8500000000004 1849372.0 NULL 3.96436076E8 7196.0 37.611 39.0 NULL +1969-12-31 15:59:43.771 15601.0 NULL NULL 49.0 -15601.0 -21239.15 -4009457.0 NULL -1.10733693E9 -15601.0 -50.389 -49.0 NULL +1969-12-31 15:59:43.773 -200.0 NULL NULL -24.0 200.0 -5438.15 51400.0 NULL -1.046049502E9 200.0 22.611 24.0 NULL +1969-12-31 15:59:43.782 -7196.0 NULL NULL 51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.607339819E9 7196.0 -52.389 -51.0 NULL +1969-12-31 15:59:43.783 -200.0 NULL NULL -11.0 200.0 -5438.15 51400.0 NULL 1.2116287E7 200.0 9.611 11.0 NULL +1969-12-31 15:59:43.807 -7196.0 NULL NULL 42.0 7196.0 1557.8500000000004 1849372.0 NULL -5.98226333E8 7196.0 -43.389 -42.0 NULL +1969-12-31 15:59:43.82 -7196.0 NULL NULL -30.0 7196.0 1557.8500000000004 1849372.0 NULL 1.329550715E9 7196.0 28.611 30.0 NULL diff --git ql/src/test/results/clientpositive/parquet_vectorization_9.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_9.q.out similarity index 84% rename from ql/src/test/results/clientpositive/parquet_vectorization_9.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_9.q.out index da42363e45..e547554170 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_9.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_9.q.out @@ -52,89 +52,115 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 12288 Data size: 2183514 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) - predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) - Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [6, 5, 8, 13] - selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) - Group By Vectorization: - aggregators: VectorUDAFCount(col 5:double) -> bigint, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFMinDouble(col 5:double) -> double - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 6:string, col 5:double, col 8:timestamp - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3] - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) + Statistics: Num rows: 12288 Data size: 2183514 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 7:string, pattern %b%), FilterExprOrExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -1.389), FilterStringGroupColLessStringScalar(col 6:string, val a))) + predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389D) or (cstring1 < 'a'))) (type: boolean) + Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp), (cdouble * cdouble) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [6, 5, 8, 13] + selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double + Statistics: Num rows: 6144 Data size: 1091808 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1), sum(_col3), sum(_col1), min(_col1) + Group By Vectorization: + aggregators: VectorUDAFCount(col 5:double) -> bigint, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFMinDouble(col 5:double) -> double + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 6:string, col 5:double, col 8:timestamp + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1, 2, 3] + keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), min(VALUE._col3) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFMinDouble(col 6:double) -> double + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:string, col 1:double, col 2:timestamp + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0, 1, 2, 3] + keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2, 7, 9, 3, 17, 26, 36, 6, 37, 39, 47] + selectExpressions: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 7:double, DoubleColUnaryMinus(col 8:double)(children: DoubleColSubtractDoubleScalar(col 1:double, val 9763215.5639) -> 8:double) -> 9:double, FuncPowerDoubleToDouble(col 16:double)(children: DoubleColDivideLongColumn(col 12:double, col 15:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 10:double) -> 11:double) -> 12:double, IfExprNullCondExpr(col 13:boolean, null, col 14:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 14:bigint) -> 15:bigint) -> 16:double) -> 17:double, DoubleColUnaryMinus(col 25:double)(children: FuncPowerDoubleToDouble(col 24:double)(children: DoubleColDivideLongColumn(col 20:double, col 23:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 19:double)(children: DoubleColDivideLongColumn(col 18:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 18:double) -> 19:double) -> 20:double, IfExprNullCondExpr(col 21:boolean, null, col 22:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 21:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 22:bigint) -> 23:bigint) -> 24:double) -> 25:double) -> 26:double, DoubleColMultiplyDoubleColumn(col 34:double, col 35:double)(children: FuncPowerDoubleToDouble(col 33:double)(children: DoubleColDivideLongColumn(col 29:double, col 32:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 28:double)(children: DoubleColDivideLongColumn(col 27:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 27:double) -> 28:double) -> 29:double, IfExprNullCondExpr(col 30:boolean, null, col 31:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 30:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 31:bigint) -> 32:bigint) -> 33:double) -> 34:double, CastLongToDouble(col 3:bigint) -> 35:double) -> 36:double, DoubleScalarDivideDoubleColumn(val 9763215.5639, col 1:double) -> 37:double, DecimalColDivideDecimalScalar(col 38:decimal(19,0), val -1.389)(children: CastLongToDecimal(col 3:bigint) -> 38:decimal(19,0)) -> 39:decimal(28,6), FuncPowerDoubleToDouble(col 46:double)(children: DoubleColDivideLongColumn(col 42:double, col 45:bigint)(children: DoubleColSubtractDoubleColumn(col 4:double, col 41:double)(children: DoubleColDivideLongColumn(col 40:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 40:double) -> 41:double) -> 42:double, IfExprNullCondExpr(col 43:boolean, null, col 44:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 43:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 44:bigint) -> 45:bigint) -> 46:double) -> 47:double + Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: double), _col6 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), min(VALUE._col3) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 3072 Data size: 424052 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639D) (type: double), (- (_col1 - 9763215.5639D)) (type: double), _col3 (type: bigint), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (- power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5)) (type: double), (power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) * UDFToDouble(_col3)) (type: double), _col6 (type: double), (9763215.5639D / _col1) (type: double), (CAST( _col3 AS decimal(19,0)) / -1.389) (type: decimal(28,6)), power(((_col4 - ((_col5 * _col5) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 3072 Data size: 890996 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_vectorization_decimal_date.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_decimal_date.q.out similarity index 50% rename from ql/src/test/results/clientpositive/parquet_vectorization_decimal_date.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_decimal_date.q.out index d210a3e144..1a393eb53e 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_decimal_date.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_decimal_date.q.out @@ -30,55 +30,59 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: date_decimal_test_parquet - filterExpr: (cint is not null and cdouble is not null) (type: boolean) - Statistics: Num rows: 12288 Data size: 1651440 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:double)) - predicate: (cint is not null and cdouble is not null) (type: boolean) - Statistics: Num rows: 6848 Data size: 920460 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cdate (type: date), cdecimal (type: decimal(20,10)) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [2, 3] - Statistics: Num rows: 6848 Data size: 859096 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Limit Vectorization: - className: VectorLimitOperator + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: date_decimal_test_parquet + filterExpr: (cint is not null and cdouble is not null) (type: boolean) + Statistics: Num rows: 12288 Data size: 1651440 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: native: true - Statistics: Num rows: 10 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 10 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:double)) + predicate: (cint is not null and cdouble is not null) (type: boolean) + Statistics: Num rows: 6848 Data size: 920460 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cdate (type: date), cdecimal (type: decimal(20,10)) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [2, 3] + Statistics: Num rows: 6848 Data size: 859096 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 10 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 10 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_div0.q.out similarity index 51% rename from ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_div0.q.out index f4022dfcd7..e6a8118f7e 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_div0.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_div0.q.out @@ -18,48 +18,52 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Select Operator - expressions: (cdouble / 0.0D) (type: double) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [13] - selectExpressions: DoubleColDivideDoubleScalar(col 5:double, val 0.0) -> 13:double - Statistics: Num rows: 12288 Data size: 98304 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 100 - Limit Vectorization: - className: VectorLimitOperator - native: true - Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Select Operator + expressions: (cdouble / 0.0D) (type: double) + outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [13] + selectExpressions: DoubleColDivideDoubleScalar(col 5:double, val 0.0) -> 13:double + Statistics: Num rows: 12288 Data size: 98304 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 100 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true Stage: Stage-0 Fetch Operator @@ -197,71 +201,101 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cbigint > 0L) and (cbigint < 100000000L)) (type: boolean) - Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val 0), FilterLongColLessLongScalar(col 3:bigint, val 100000000)) - predicate: ((cbigint > 0L) and (cbigint < 100000000L)) (type: boolean) - Statistics: Num rows: 3215 Data size: 38416 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cbigint > 0L) and (cbigint < 100000000L)) (type: boolean) + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterLongScalar(col 3:bigint, val 0), FilterLongColLessLongScalar(col 3:bigint, val 100000000)) + predicate: ((cbigint > 0L) and (cbigint < 100000000L)) (type: boolean) + Statistics: Num rows: 3215 Data size: 38416 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: (cbigint - 988888L) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888L))) (type: double) + null sort order: zz + Statistics: Num rows: 3215 Data size: 38416 Basic stats: COMPLETE Column stats: COMPLETE + top n: 100 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 13:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 15:double) -> 16:double + native: true + Select Operator + expressions: (cbigint - 988888L) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888L))) (type: double), (1.2 / CAST( (cbigint - 988888L) AS decimal(19,0))) (type: decimal(22,21)) + outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [14, 18, 21] + selectExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 17:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 17:bigint) -> 15:double) -> 18:double, DecimalScalarDivideDecimalColumn(val 1.2, col 20:decimal(19,0))(children: CastLongToDecimal(col 19:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 19:bigint) -> 20:decimal(19,0)) -> 21:decimal(22,21) + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: bigint), _col1 (type: double) + null sort order: zz + sort order: ++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(22,21)) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Select Operator - expressions: (cbigint - 988888L) (type: bigint), (cdouble / UDFToDouble((cbigint - 988888L))) (type: double), (1.2 / CAST( (cbigint - 988888L) AS decimal(19,0))) (type: decimal(22,21)) + expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: decimal(22,21)) outputColumnNames: _col0, _col1, _col2 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [13, 16, 19] - selectExpressions: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 13:bigint, DoubleColDivideDoubleColumn(col 5:double, col 15:double)(children: CastLongToDouble(col 14:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 14:bigint) -> 15:double) -> 16:double, DecimalScalarDivideDecimalColumn(val 1.2, col 18:decimal(19,0))(children: CastLongToDecimal(col 17:bigint)(children: LongColSubtractLongScalar(col 3:bigint, val 988888) -> 17:bigint) -> 18:decimal(19,0)) -> 19:decimal(22,21) + projectedOutputColumnNums: [0, 1, 2] Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: bigint), _col1 (type: double) - null sort order: zz - sort order: ++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: decimal(22,21)) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: decimal(22,21)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3215 Data size: 411520 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 100 - Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Limit + Number of rows: 100 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 100 Data size: 12800 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -401,71 +435,101 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cdouble >= -500.0D) and (cdouble < -199.0D)) (type: boolean) - Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -500.0), FilterDoubleColLessDoubleScalar(col 5:double, val -199.0)) - predicate: ((cdouble >= -500.0D) and (cdouble < -199.0D)) (type: boolean) - Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cdouble >= -500.0D) and (cdouble < -199.0D)) (type: boolean) + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5:double, val -500.0), FilterDoubleColLessDoubleScalar(col 5:double, val -199.0)) + predicate: ((cdouble >= -500.0D) and (cdouble < -199.0D)) (type: boolean) + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double) + null sort order: zz + Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE + top n: 100 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 13:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 16:double + native: true + Select Operator + expressions: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), ((cdouble + 200.0D) / (cdouble + 200.0D)) (type: double), (3.0D / (cdouble + 200.0D)) (type: double), (1.2D / (cdouble + 200.0D)) (type: double) + outputColumnNames: _col0, _col1, _col2, _col4, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [14, 18, 20, 21, 22] + selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 14:double, DoubleColDivideDoubleColumn(col 15:double, col 17:double)(children: CastLongToDouble(col 3:bigint) -> 15:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 17:double) -> 18:double, DoubleColDivideDoubleColumn(col 15:double, col 19:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 19:double) -> 20:double, DoubleScalarDivideDoubleColumn(val 3.0, col 15:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 21:double, DoubleScalarDivideDoubleColumn(val 1.2, col 15:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 22:double + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double), _col1 (type: double) + null sort order: zz + sort order: ++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: Select Operator - expressions: (cdouble + 200.0D) (type: double), (UDFToDouble(cbigint) / (cdouble + 200.0D)) (type: double), ((cdouble + 200.0D) / (cdouble + 200.0D)) (type: double), (3.0D / (cdouble + 200.0D)) (type: double), (1.2D / (cdouble + 200.0D)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col4, _col5 + expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [13, 16, 19, 21, 23] - selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 13:double, DoubleColDivideDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 3:bigint) -> 14:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 15:double) -> 16:double, DoubleColDivideDoubleColumn(col 17:double, col 18:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 17:double, DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 18:double) -> 19:double, DoubleScalarDivideDoubleColumn(val 3.0, col 20:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 20:double) -> 21:double, DoubleScalarDivideDoubleColumn(val 1.2, col 22:double)(children: DoubleColAddDoubleScalar(col 5:double, val 200.0) -> 22:double) -> 23:double + projectedOutputColumnNums: [0, 1, 2, 1, 3, 4] Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: double), _col1 (type: double) - null sort order: zz - sort order: ++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false + Limit + Number of rows: 100 + Limit Vectorization: + className: VectorLimitOperator + native: true Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: double), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 100 - Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 960 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_limit.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_limit.q.out new file mode 100644 index 0000000000..06d094bb97 --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_limit.q.out @@ -0,0 +1,993 @@ +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble AND cint > 0 ORDER BY cbigint, cdouble LIMIT 7 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble AND cint > 0 ORDER BY cbigint, cdouble LIMIT 7 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) + Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: cbigint (type: bigint), cdouble (type: double) + null sort order: zz + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE + top n: 7 + Select Operator + expressions: cbigint (type: bigint), cdouble (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2048 Data size: 16176 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: bigint), _col1 (type: double) + null sort order: zz + sort order: ++ + Statistics: Num rows: 2048 Data size: 16176 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2048 Data size: 16176 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 7 + Statistics: Num rows: 7 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 7 + Processor Tree: + ListSink + +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble AND cint > 0 ORDER BY cbigint, cdouble LIMIT 7 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble AND cint > 0 ORDER BY cbigint, cdouble LIMIT 7 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-1887561756 -15891.0 +-1887561756 -15951.0 +-1887561756 -16008.0 +-1887561756 -16183.0 +-1887561756 -16225.0 +-1887561756 -16243.0 +-1887561756 -16296.0 +PREHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble,csmallint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble,csmallint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ctinyint is not null (type: boolean) + Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 0:tinyint) + predicate: ctinyint is not null (type: boolean) + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: +++ + keys: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) + null sort order: zzz + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 0:tinyint, col 5:double, col 1:smallint + native: true + Select Operator + expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) + outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5, 1] + Statistics: Num rows: 9173 Data size: 72384 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: double), _col2 (type: smallint) + null sort order: zzz + sort order: +++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 9173 Data size: 72384 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: smallint) + outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2] + Statistics: Num rows: 9173 Data size: 72384 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 20 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble,csmallint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble,csmallint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-64 -10462.0 -10462 +-64 -15920.0 -15920 +-64 -1600.0 -1600 +-64 -200.0 -200 +-64 -2919.0 -2919 +-64 -3097.0 -3097 +-64 -3586.0 -3586 +-64 -4018.0 -4018 +-64 -4040.0 -4040 +-64 -4803.0 -4803 +-64 -6907.0 -6907 +-64 -7196.0 -7196 +-64 -7196.0 -7196 +-64 -7196.0 -7196 +-64 -7196.0 -7196 +-64 -7196.0 -7196 +-64 -7196.0 -7196 +-64 -7196.0 -7196 +-64 -8080.0 -8080 +-64 -9842.0 -9842 +PREHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Top N Key Operator + sort order: + + keys: ctinyint (type: tinyint) + null sort order: z + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 0:tinyint + native: true + Select Operator + expressions: ctinyint (type: tinyint), (cdouble + 1.0D) (type: double) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 13] + selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 1.0) -> 13:double + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col1), count(_col1) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFCount(col 13:double) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 0:tinyint + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0, 1] + keys: _col0 (type: tinyint) + minReductionHashAggr: 0.9893392 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 131 Data size: 2360 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 131 Data size: 2360 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: double), _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1) + Group By Vectorization: + aggregators: VectorUDAFSumDouble(col 1:double) -> double, VectorUDAFCountMerge(col 2:bigint) -> bigint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:tinyint + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0, 1] + keys: KEY._col0 (type: tinyint) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 131 Data size: 2360 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: tinyint), (_col1 / _col2) (type: double) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 3] + selectExpressions: DoubleColDivideLongColumn(col 1:double, col 2:bigint) -> 3:double + Statistics: Num rows: 131 Data size: 1312 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 20 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-45 326.44444444444446 +-46 3033.55 +-47 -574.6428571428571 +-48 1672.909090909091 +-49 768.7659574468086 +-50 -960.0192307692307 +-51 -96.46341463414635 +-52 2810.705882352941 +-53 -532.7567567567568 +-54 2712.7272727272725 +-55 2385.595744680851 +-56 2595.818181818182 +-57 1867.0535714285713 +-58 3483.2444444444445 +-59 318.27272727272725 +-60 1071.82 +-61 914.3404255319149 +-62 245.69387755102042 +-63 2178.7272727272725 +-64 373.52941176470586 +PREHOOK: query: explain VECTORIZATION EXPRESSION +select distinct(ctinyint) from alltypesparquet order by ctinyint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain VECTORIZATION EXPRESSION +select distinct(ctinyint) from alltypesparquet order by ctinyint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Top N Key Operator + sort order: + + keys: ctinyint (type: tinyint) + null sort order: z + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 0:tinyint + native: true + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: ctinyint + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0] + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 0:tinyint + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [] + keys: ctinyint (type: tinyint) + minReductionHashAggr: 0.9893392 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 131 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 131 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:tinyint + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [] + keys: KEY._col0 (type: tinyint) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 131 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: tinyint) + outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0] + Limit + Number of rows: 20 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: select distinct(ctinyint) from alltypesparquet order by ctinyint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: select distinct(ctinyint) from alltypesparquet order by ctinyint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-45 +-46 +-47 +-48 +-49 +-50 +-51 +-52 +-53 +-54 +-55 +-56 +-57 +-58 +-59 +-60 +-61 +-62 +-63 +-64 +PREHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Top N Key Operator + sort order: + + keys: ctinyint (type: tinyint) + null sort order: z + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 0:tinyint + native: true + Select Operator + expressions: ctinyint (type: tinyint), cdouble (type: double) + outputColumnNames: ctinyint, cdouble + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5] + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 0:tinyint, col 5:double + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [] + keys: ctinyint (type: tinyint), cdouble (type: double) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6144 Data size: 36368 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: double) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: tinyint) + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 6144 Data size: 36368 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:tinyint, col 1:double + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [] + keys: KEY._col0 (type: tinyint), KEY._col1 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6144 Data size: 36368 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + Group By Vectorization: + aggregators: VectorUDAFCount(col 1:double) -> bigint + className: VectorGroupByOperator + groupByMode: COMPLETE + keyExpressions: col 0:tinyint + native: false + vectorProcessingMode: STREAMING + projectedOutputColumnNums: [0] + keys: _col0 (type: tinyint) + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 131 Data size: 1312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: tinyint), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1] + Limit + Number of rows: 20 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-45 24 +-46 24 +-47 22 +-48 29 +-49 26 +-50 30 +-51 21 +-52 33 +-53 22 +-54 26 +-55 29 +-56 36 +-57 35 +-58 23 +-59 31 +-60 27 +-61 25 +-62 27 +-63 19 +-64 24 +PREHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint,cdouble from alltypesparquet order by ctinyint,cdouble limit 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain VECTORIZATION EXPRESSION +select ctinyint,cdouble from alltypesparquet order by ctinyint,cdouble limit 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 0 + Processor Tree: + ListSink + +PREHOOK: query: select ctinyint,cdouble from alltypesparquet order by ctinyint,cdouble limit 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: select ctinyint,cdouble from alltypesparquet order by ctinyint,cdouble limit 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PREHOOK: query: explain VECTORIZATION EXPRESSION +select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain VECTORIZATION EXPRESSION +select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ctinyint is not null (type: boolean) + Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 0:tinyint) + predicate: ctinyint is not null (type: boolean) + Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(ctinyint) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 0:tinyint) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 5:double + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: cdouble (type: double) + minReductionHashAggr: 0.49994552 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: double) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint + className: VectorGroupByOperator + groupByMode: MERGEPARTIAL + keyExpressions: col 0:double + native: false + vectorProcessingMode: MERGE_PARTIAL + projectedOutputColumnNums: [0] + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: _col1 (type: bigint), _col0 (type: double) + null sort order: zz + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 1:bigint, col 0:double + native: true + Reduce Output Operator + key expressions: _col1 (type: bigint), _col0 (type: double) + null sort order: zz + sort order: ++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + Reducer 3 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [1, 0] + Statistics: Num rows: 4586 Data size: 54792 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 20 + Limit Vectorization: + className: VectorLimitOperator + native: true + Statistics: Num rows: 20 Data size: 248 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 20 Data size: 248 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + ListSink + +PREHOOK: query: select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-10462.0 -64 +-1121.0 -89 +-11322.0 -101 +-11492.0 -78 +-15920.0 -64 +-4803.0 -64 +-6907.0 -64 +-7196.0 -2009 +-8080.0 -64 +-8118.0 -80 +-9842.0 -64 +10496.0 -67 +15601.0 -1733 +3520.0 -86 +4811.0 -115 +5241.0 -80 +557.0 -75 +7705.0 -88 +9452.0 -76 +NULL -32768 diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_offset_limit.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_offset_limit.q.out new file mode 100644 index 0000000000..bd362f763c --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_offset_limit.q.out @@ -0,0 +1,208 @@ +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) + Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) + Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint), cdouble (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 2 + Offset of rows: 3 + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + + Stage: Stage-0 + Fetch Operator + limit: 2 + Processor Tree: + ListSink + +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-1887561756 10361.0 +-1887561756 -8881.0 +PREHOOK: query: explain vectorization expression +select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization expression +select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: ctinyint is not null (type: boolean) + Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsNotNull(col 0:tinyint) + predicate: ctinyint is not null (type: boolean) + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: ctinyint (type: tinyint), cdouble (type: double) + null sort order: zz + Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE + top n: 13 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 0:tinyint, col 5:double + native: true + Select Operator + expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) + outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 5, 1] + Statistics: Num rows: 9173 Data size: 72384 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: double) + null sort order: zz + sort order: ++ + Reduce Sink Vectorization: + className: VectorReduceSinkObjectHashOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 9173 Data size: 72384 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: smallint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) + outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 2] + Statistics: Num rows: 9173 Data size: 72384 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Limit Vectorization: + className: VectorLimitOperator + native: true + Offset of rows: 10 + Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + ListSink + +PREHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-64 -7196.0 -7196 +-64 -6907.0 -6907 +-64 -4803.0 -4803 diff --git ql/src/test/results/clientpositive/parquet_vectorization_part_project.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_part_project.q.out similarity index 72% rename from ql/src/test/results/clientpositive/parquet_vectorization_part_project.q.out rename to ql/src/test/results/clientpositive/llap/parquet_vectorization_part_project.q.out index acf90fd643..49843ec870 100644 --- ql/src/test/results/clientpositive/parquet_vectorization_part_project.q.out +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_part_project.q.out @@ -68,50 +68,67 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet_part_n0 - Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (cdouble + 2.0D) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: double) - null sort order: z - sort order: + + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet_part_n0 + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: (cdouble + 2.0D) (type: double) + null sort order: z + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + top n: 10 + Select Operator + expressions: (cdouble + 2.0D) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + null sort order: z + sort order: + + Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: true + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: double) + outputColumnNames: _col0 Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/parquet_vectorization_pushdown.q.out ql/src/test/results/clientpositive/llap/parquet_vectorization_pushdown.q.out new file mode 100644 index 0000000000..509d1386e0 --- /dev/null +++ ql/src/test/results/clientpositive/llap/parquet_vectorization_pushdown.q.out @@ -0,0 +1,102 @@ +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: explain vectorization SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesparquet + filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) + Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) + Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint) + outputColumnNames: cbigint + Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(cbigint), count(cbigint) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs (cache only) + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reducer 2 + Execution mode: vectorized, llap + Reduce Vectorization: + enabled: true + enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToDouble(_col0) / _col1) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +WARNING: Comparing a bigint and a double may result in a loss of precision. +PREHOOK: query: SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +POSTHOOK: query: SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesparquet +#### A masked pattern was here #### +-1.4670720493864927E9 diff --git ql/src/test/results/clientpositive/partial_column_stats.q.out ql/src/test/results/clientpositive/llap/partial_column_stats.q.out similarity index 51% rename from ql/src/test/results/clientpositive/partial_column_stats.q.out rename to ql/src/test/results/clientpositive/llap/partial_column_stats.q.out index 2e58c060d1..00dc5406d7 100644 --- ql/src/test/results/clientpositive/partial_column_stats.q.out +++ ql/src/test/results/clientpositive/llap/partial_column_stats.q.out @@ -18,45 +18,55 @@ POSTHOOK: Output: default@t1_n53 #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n53 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n53 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1068 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: Column Stats Desc: diff --git ql/src/test/results/clientpositive/llap/partition_boolexpr.q.out ql/src/test/results/clientpositive/llap/partition_boolexpr.q.out new file mode 100644 index 0000000000..101079dd50 --- /dev/null +++ ql/src/test/results/clientpositive/llap/partition_boolexpr.q.out @@ -0,0 +1,317 @@ +PREHOOK: query: create table part_boolexpr(key int, value string) partitioned by (dt int, ts string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@part_boolexpr +POSTHOOK: query: create table part_boolexpr(key int, value string) partitioned by (dt int, ts string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@part_boolexpr +PREHOOK: query: select count(*) from part_boolexpr where key = 'abc' +PREHOOK: type: QUERY +PREHOOK: Input: default@part_boolexpr +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from part_boolexpr where key = 'abc' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@part_boolexpr +#### A masked pattern was here #### +0 +PREHOOK: query: select * from part_boolexpr where dt = 'abc' +PREHOOK: type: QUERY +PREHOOK: Input: default@part_boolexpr +#### A masked pattern was here #### +POSTHOOK: query: select * from part_boolexpr where dt = 'abc' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@part_boolexpr +#### A masked pattern was here #### +PREHOOK: query: explain select count(1) from srcpart where true +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +#### A masked pattern was here #### +POSTHOOK: query: explain select count(1) from srcpart where true +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: explain select count(1) from srcpart where false +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: explain select count(1) from srcpart where false +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select count(1) from srcpart where true and hr='11' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +#### A masked pattern was here #### +POSTHOOK: query: explain select count(1) from srcpart where true and hr='11' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: explain select count(1) from srcpart where true or hr='11' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +#### A masked pattern was here #### +POSTHOOK: query: explain select count(1) from srcpart where true or hr='11' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: explain select count(1) from srcpart where false or hr='11' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +#### A masked pattern was here #### +POSTHOOK: query: explain select count(1) from srcpart where false or hr='11' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: explain select count(1) from srcpart where false and hr='11' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: explain select count(1) from srcpart where false and hr='11' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select count(1) from srcpart where INPUT__FILE__NAME is not null +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: explain select count(1) from srcpart where INPUT__FILE__NAME is not null +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: INPUT__FILE__NAME is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: INPUT__FILE__NAME is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/partition_condition_remover.q.out ql/src/test/results/clientpositive/llap/partition_condition_remover.q.out similarity index 94% rename from ql/src/test/results/clientpositive/partition_condition_remover.q.out rename to ql/src/test/results/clientpositive/llap/partition_condition_remover.q.out index 71671e7395..9b511700fd 100644 --- ql/src/test/results/clientpositive/partition_condition_remover.q.out +++ ql/src/test/results/clientpositive/llap/partition_condition_remover.q.out @@ -49,11 +49,9 @@ STAGE PLANS: TableScan alias: foo_n5 filterExpr: (s <> 'bar') (type: boolean) - Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: i (type: int), s (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from foo_n5 where s not in ('bar') diff --git ql/src/test/results/clientpositive/partition_timestamp2.q.out ql/src/test/results/clientpositive/llap/partition_timestamp2.q.out similarity index 100% rename from ql/src/test/results/clientpositive/partition_timestamp2.q.out rename to ql/src/test/results/clientpositive/llap/partition_timestamp2.q.out index 0928abf952..22312412ac 100644 --- ql/src/test/results/clientpositive/partition_timestamp2.q.out +++ ql/src/test/results/clientpositive/llap/partition_timestamp2.q.out @@ -56,10 +56,10 @@ POSTHOOK: Input: default@partition_timestamp2_1@dt=1999-01-01 01%3A00%3A00/regio POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 00%3A00%3A00/region=1 POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 01%3A00%3A00/region=1 #### A masked pattern was here #### +2000-01-01 01:00:00 1999-01-01 00:00:00 1999-01-01 01:00:00 2000-01-01 00:00:00 -2000-01-01 01:00:00 PREHOOK: query: select * from partition_timestamp2_1 PREHOOK: type: QUERY PREHOOK: Input: default@partition_timestamp2_1 @@ -135,9 +135,9 @@ POSTHOOK: Input: default@partition_timestamp2_1@dt=1999-01-01 01%3A00%3A00/regio POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 00%3A00%3A00/region=1 POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 01%3A00%3A00/region=1 #### A masked pattern was here #### +2000-01-01 01:00:00 1999-01-01 00:00:00 1999-01-01 01:00:00 -2000-01-01 01:00:00 PREHOOK: query: select * from partition_timestamp2_1 PREHOOK: type: QUERY PREHOOK: Input: default@partition_timestamp2_1 @@ -182,9 +182,9 @@ POSTHOOK: Input: default@partition_timestamp2_1@dt=1999-01-01 01%3A00%3A00/regio POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 00%3A00%3A00/region=1 POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 01%3A00%3A00/region=1 #### A masked pattern was here #### +2000-01-01 01:00:00 1999-01-01 00:00:00 1999-01-01 01:00:00 -2000-01-01 01:00:00 PREHOOK: query: select * from partition_timestamp2_1 PREHOOK: type: QUERY PREHOOK: Input: default@partition_timestamp2_1 @@ -230,8 +230,8 @@ POSTHOOK: Input: default@partition_timestamp2_1@dt=1999-01-01 00%3A00%3A00/regio POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 00%3A00%3A00/region=1 POSTHOOK: Input: default@partition_timestamp2_1@dt=2000-01-01 01%3A00%3A00/region=1 #### A masked pattern was here #### -1999-01-01 00:00:00 2000-01-01 01:00:00 +1999-01-01 00:00:00 PREHOOK: query: select * from partition_timestamp2_1 PREHOOK: type: QUERY PREHOOK: Input: default@partition_timestamp2_1 diff --git ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out ql/src/test/results/clientpositive/llap/partition_wise_fileformat2.q.out similarity index 94% rename from ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out rename to ql/src/test/results/clientpositive/llap/partition_wise_fileformat2.q.out index 6d1d25a8cb..30331d21d3 100644 --- ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out +++ ql/src/test/results/clientpositive/llap/partition_wise_fileformat2.q.out @@ -77,14 +77,11 @@ STAGE PLANS: TableScan alias: partition_test_partitioned filterExpr: UDFToDouble(dt) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 75 Data size: 26925 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: UDFToDouble(dt) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 8 Data size: 2872 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), dt (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 2936 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select * from partition_test_partitioned where dt >=100 and dt <= 102 @@ -101,6 +98,31 @@ POSTHOOK: Input: default@partition_test_partitioned@dt=100 POSTHOOK: Input: default@partition_test_partitioned@dt=101 POSTHOOK: Input: default@partition_test_partitioned@dt=102 #### A masked pattern was here #### +238 val_238 100 + 100 +311 val_311 100 + val_27 100 + val_165 100 + val_409 100 +255 val_255 100 +278 val_278 100 +98 val_98 100 + val_484 100 + val_265 100 + val_193 100 +401 val_401 100 +150 val_150 100 +273 val_273 100 +224 100 +369 100 +66 val_66 100 +128 100 +213 val_213 100 +146 val_146 100 +406 val_406 100 + 100 + 100 + 100 238 val_238 102 102 311 val_311 102 @@ -151,31 +173,6 @@ POSTHOOK: Input: default@partition_test_partitioned@dt=102 101 101 101 -238 val_238 100 - 100 -311 val_311 100 - val_27 100 - val_165 100 - val_409 100 -255 val_255 100 -278 val_278 100 -98 val_98 100 - val_484 100 - val_265 100 - val_193 100 -401 val_401 100 -150 val_150 100 -273 val_273 100 -224 100 -369 100 -66 val_66 100 -128 100 -213 val_213 100 -146 val_146 100 -406 val_406 100 - 100 - 100 - 100 PREHOOK: query: explain select *, BLOCK__OFFSET__INSIDE__FILE from partition_test_partitioned where dt >=100 and dt <= 102 PREHOOK: type: QUERY PREHOOK: Input: default@partition_test_partitioned @@ -201,14 +198,11 @@ STAGE PLANS: TableScan alias: partition_test_partitioned filterExpr: UDFToDouble(dt) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 75 Data size: 26925 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: UDFToDouble(dt) BETWEEN 100.0D AND 102.0D (type: boolean) - Statistics: Num rows: 8 Data size: 2872 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: key (type: string), value (type: string), dt (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 2936 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select * from partition_test_partitioned where dt >=100 and dt <= 102 @@ -225,6 +219,31 @@ POSTHOOK: Input: default@partition_test_partitioned@dt=100 POSTHOOK: Input: default@partition_test_partitioned@dt=101 POSTHOOK: Input: default@partition_test_partitioned@dt=102 #### A masked pattern was here #### +238 val_238 100 + 100 +311 val_311 100 + val_27 100 + val_165 100 + val_409 100 +255 val_255 100 +278 val_278 100 +98 val_98 100 + val_484 100 + val_265 100 + val_193 100 +401 val_401 100 +150 val_150 100 +273 val_273 100 +224 100 +369 100 +66 val_66 100 +128 100 +213 val_213 100 +146 val_146 100 +406 val_406 100 + 100 + 100 + 100 238 val_238 102 102 311 val_311 102 @@ -275,28 +294,3 @@ POSTHOOK: Input: default@partition_test_partitioned@dt=102 101 101 101 -238 val_238 100 - 100 -311 val_311 100 - val_27 100 - val_165 100 - val_409 100 -255 val_255 100 -278 val_278 100 -98 val_98 100 - val_484 100 - val_265 100 - val_193 100 -401 val_401 100 -150 val_150 100 -273 val_273 100 -224 100 -369 100 -66 val_66 100 -128 100 -213 val_213 100 -146 val_146 100 -406 val_406 100 - 100 - 100 - 100 diff --git ql/src/test/results/clientpositive/llap/pcr.q.out ql/src/test/results/clientpositive/llap/pcr.q.out new file mode 100644 index 0000000000..755acde898 --- /dev/null +++ ql/src/test/results/clientpositive/llap/pcr.q.out @@ -0,0 +1,5523 @@ +PREHOOK: query: drop table pcr_t1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table pcr_t2 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t2 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table pcr_t3 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t3 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t1 +POSTHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t1 +PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-08') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1@ds=2000-04-08 +POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-08') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-09') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1@ds=2000-04-09 +POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-09') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-10') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1@ds=2000-04-10 +POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-10') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1@ds=2000-04-10 +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE `key` < 5 AND `ds` <= '2000-04-09' +ORDER BY `key`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: ((key < 5) and (ds <= '2000-04-09')) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key < 5) (type: boolean) + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +0 val_0 2000-04-08 +0 val_0 2000-04-08 +0 val_0 2000-04-08 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +2 val_2 2000-04-08 +2 val_2 2000-04-09 +4 val_4 2000-04-08 +4 val_4 2000-04-09 +PREHOOK: query: explain extended select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value` +FROM `default`.`pcr_t1` +WHERE `key` < 5 OR `ds` <= '2000-04-09' +ORDER BY `key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: ((key < 5) or (ds <= '2000-04-09')) (type: boolean) + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key < 5) or (ds <= '2000-04-09')) (type: boolean) + Statistics: Num rows: 36 Data size: 10008 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-10 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +2 val_2 +2 val_2 +4 val_4 +4 val_4 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +8 val_8 +9 val_9 +9 val_9 +10 val_10 +10 val_10 +11 val_11 +11 val_11 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +17 val_17 +17 val_17 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +19 val_19 +19 val_19 +PREHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE `key` < 5 AND `value` <> 'val_2' AND `ds` <= '2000-04-09' +ORDER BY `key`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: ((key < 5) and (value <> 'val_2')) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key < 5) and (value <> 'val_2')) (type: boolean) + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +0 val_0 2000-04-08 +0 val_0 2000-04-08 +0 val_0 2000-04-08 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +4 val_4 2000-04-08 +4 val_4 2000-04-09 +PREHOOK: query: explain extended +select key, value, ds from pcr_t1 +where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds from pcr_t1 +where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE `ds` < '2000-04-09' AND `key` < 5 OR `ds` > '2000-04-09' AND `value` = 'val_5' +ORDER BY `key`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-10 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 +where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 +where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +0 val_0 2000-04-08 +0 val_0 2000-04-08 +0 val_0 2000-04-08 +2 val_2 2000-04-08 +4 val_4 2000-04-08 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +PREHOOK: query: explain extended +select key, value, ds from pcr_t1 +where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds from pcr_t1 +where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE `ds` < '2000-04-10' AND `key` < 5 OR `ds` > '2000-04-08' AND `value` = 'val_5' +ORDER BY `key`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-10 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 +where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 +where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +0 val_0 2000-04-08 +0 val_0 2000-04-08 +0 val_0 2000-04-08 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +2 val_2 2000-04-08 +2 val_2 2000-04-09 +4 val_4 2000-04-08 +4 val_4 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +PREHOOK: query: explain extended +select key, value, ds from pcr_t1 +where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds from pcr_t1 +where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE (`ds` < '2000-04-10' OR `key` < 5) AND (`ds` > '2000-04-08' OR `value` = 'val_5') +ORDER BY `key`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-10 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 +where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 +where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-10 +0 val_0 2000-04-10 +0 val_0 2000-04-10 +2 val_2 2000-04-09 +2 val_2 2000-04-10 +4 val_4 2000-04-09 +4 val_4 2000-04-10 +5 val_5 2000-04-08 +5 val_5 2000-04-08 +5 val_5 2000-04-08 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +8 val_8 2000-04-09 +9 val_9 2000-04-09 +10 val_10 2000-04-09 +11 val_11 2000-04-09 +12 val_12 2000-04-09 +12 val_12 2000-04-09 +15 val_15 2000-04-09 +15 val_15 2000-04-09 +17 val_17 2000-04-09 +18 val_18 2000-04-09 +18 val_18 2000-04-09 +19 val_19 2000-04-09 +PREHOOK: query: explain extended select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT CAST(14 AS INTEGER) AS `key`, `value` +FROM (SELECT `value` +FROM `default`.`pcr_t1` +WHERE `key` = 14 AND `ds` IN ('2000-04-08', '2000-04-09') +ORDER BY `value`) AS `t1` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: ((key = 14) and (ds) IN ('2000-04-08', '2000-04-09')) (type: boolean) + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 14) (type: boolean) + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: 14 (type: int), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +PREHOOK: query: explain extended select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value` +FROM `default`.`pcr_t1` +WHERE `ds` IN ('2000-04-08', '2000-04-09') +ORDER BY `key`, `value` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +2 val_2 +4 val_4 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +8 val_8 +9 val_9 +9 val_9 +10 val_10 +10 val_10 +11 val_11 +11 val_11 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +17 val_17 +17 val_17 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +19 val_19 +19 val_19 +PREHOOK: query: explain extended select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value` +FROM `default`.`pcr_t1` +WHERE `ds` >= '2000-04-08' OR `ds` < '2000-04-10' +ORDER BY `key`, `value` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: ((ds >= '2000-04-08') or (ds < '2000-04-10')) (type: boolean) + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-10 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +2 val_2 +2 val_2 +4 val_4 +4 val_4 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +8 val_8 +8 val_8 +9 val_9 +9 val_9 +9 val_9 +10 val_10 +10 val_10 +10 val_10 +11 val_11 +11 val_11 +11 val_11 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +12 val_12 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +15 val_15 +17 val_17 +17 val_17 +17 val_17 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +18 val_18 +19 val_19 +19 val_19 +19 val_19 +PREHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE ROW(`key`, `ds`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) +ORDER BY `key`, `value`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +2 val_2 2000-04-09 +PREHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`pcr_t1` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`pcr_t1` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t0`.`key`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +#### A masked pattern was here #### +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +2 val_2 2000-04-08 2 val_2 2000-04-08 +4 val_4 2000-04-08 4 val_4 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +8 val_8 2000-04-08 8 val_8 2000-04-08 +9 val_9 2000-04-08 9 val_9 2000-04-08 +10 val_10 2000-04-08 10 val_10 2000-04-08 +11 val_11 2000-04-08 11 val_11 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +17 val_17 2000-04-08 17 val_17 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +19 val_19 2000-04-08 19 val_19 2000-04-08 +PREHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`pcr_t1` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`pcr_t1` +WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t0`.`key`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-09 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +#### A masked pattern was here #### +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +0 val_0 2000-04-08 0 val_0 2000-04-09 +2 val_2 2000-04-08 2 val_2 2000-04-09 +4 val_4 2000-04-08 4 val_4 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +5 val_5 2000-04-08 5 val_5 2000-04-09 +8 val_8 2000-04-08 8 val_8 2000-04-09 +9 val_9 2000-04-08 9 val_9 2000-04-09 +10 val_10 2000-04-08 10 val_10 2000-04-09 +11 val_11 2000-04-08 11 val_11 2000-04-09 +12 val_12 2000-04-08 12 val_12 2000-04-09 +12 val_12 2000-04-08 12 val_12 2000-04-09 +12 val_12 2000-04-08 12 val_12 2000-04-09 +12 val_12 2000-04-08 12 val_12 2000-04-09 +15 val_15 2000-04-08 15 val_15 2000-04-09 +15 val_15 2000-04-08 15 val_15 2000-04-09 +15 val_15 2000-04-08 15 val_15 2000-04-09 +15 val_15 2000-04-08 15 val_15 2000-04-09 +17 val_17 2000-04-08 17 val_17 2000-04-09 +18 val_18 2000-04-08 18 val_18 2000-04-09 +18 val_18 2000-04-08 18 val_18 2000-04-09 +18 val_18 2000-04-08 18 val_18 2000-04-09 +18 val_18 2000-04-08 18 val_18 2000-04-09 +19 val_19 2000-04-08 19 val_19 2000-04-09 +PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-11') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1@ds=2000-04-11 +POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-11') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1@ds=2000-04-11 +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-11).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +PREHOOK: Input: default@pcr_t1@ds=2000-04-11 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-11 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE `ds` > '2000-04-08' AND `ds` < '2000-04-11' OR `ds` BETWEEN '2000-04-08' AND '2000-04-11' AND `key` = 2 +ORDER BY `key`, `value`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) + Statistics: Num rows: 80 Data size: 22240 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-10 [pcr_t1] + /pcr_t1/ds=2000-04-11 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +PREHOOK: Input: default@pcr_t1@ds=2000-04-11 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-11 +#### A masked pattern was here #### +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-10 +0 val_0 2000-04-10 +0 val_0 2000-04-10 +2 val_2 2000-04-08 +2 val_2 2000-04-09 +2 val_2 2000-04-10 +2 val_2 2000-04-11 +4 val_4 2000-04-09 +4 val_4 2000-04-10 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +8 val_8 2000-04-09 +8 val_8 2000-04-10 +9 val_9 2000-04-09 +9 val_9 2000-04-10 +10 val_10 2000-04-09 +10 val_10 2000-04-10 +11 val_11 2000-04-09 +11 val_11 2000-04-10 +12 val_12 2000-04-09 +12 val_12 2000-04-09 +12 val_12 2000-04-10 +12 val_12 2000-04-10 +15 val_15 2000-04-09 +15 val_15 2000-04-09 +15 val_15 2000-04-10 +15 val_15 2000-04-10 +17 val_17 2000-04-09 +17 val_17 2000-04-10 +18 val_18 2000-04-09 +18 val_18 2000-04-09 +18 val_18 2000-04-10 +18 val_18 2000-04-10 +19 val_19 2000-04-09 +19 val_19 2000-04-10 +PREHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1` +WHERE `ds` > '2000-04-08' AND `ds` < '2000-04-11' OR `ds` <= '2000-04-09' AND `key` = 2 +ORDER BY `key`, `value`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + filterExpr: ((ds > '2000-04-08') or ((ds <= '2000-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((ds > '2000-04-08') or ((ds <= '2000-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + /pcr_t1/ds=2000-04-09 [pcr_t1] + /pcr_t1/ds=2000-04-10 [pcr_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 +#### A masked pattern was here #### +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-10 +0 val_0 2000-04-10 +0 val_0 2000-04-10 +2 val_2 2000-04-08 +2 val_2 2000-04-09 +2 val_2 2000-04-10 +4 val_4 2000-04-09 +4 val_4 2000-04-10 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +5 val_5 2000-04-10 +8 val_8 2000-04-09 +8 val_8 2000-04-10 +9 val_9 2000-04-09 +9 val_9 2000-04-10 +10 val_10 2000-04-09 +10 val_10 2000-04-10 +11 val_11 2000-04-09 +11 val_11 2000-04-10 +12 val_12 2000-04-09 +12 val_12 2000-04-09 +12 val_12 2000-04-10 +12 val_12 2000-04-10 +15 val_15 2000-04-09 +15 val_15 2000-04-09 +15 val_15 2000-04-10 +15 val_15 2000-04-10 +17 val_17 2000-04-09 +17 val_17 2000-04-10 +18 val_18 2000-04-09 +18 val_18 2000-04-09 +18 val_18 2000-04-10 +18 val_18 2000-04-10 +19 val_19 2000-04-09 +19 val_19 2000-04-10 +PREHOOK: query: create table pcr_t2 (key int, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t2 +POSTHOOK: query: create table pcr_t2 (key int, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t2 +PREHOOK: query: create table pcr_t3 (key int, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t3 +POSTHOOK: query: create table pcr_t3 (key int, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t3 +PREHOOK: query: explain extended +from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Output: default@pcr_t2 +PREHOOK: Output: default@pcr_t3 +POSTHOOK: query: explain extended +from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Output: default@pcr_t2 +POSTHOOK: Output: default@pcr_t3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t2 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct pcr_t2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.95 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 2 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t3 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct pcr_t3 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t3 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.95 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Reducer 3 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t2 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct pcr_t2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2 + + Stage: Stage-4 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.pcr_t2 + Is Table Level Stats: true + + Stage: Stage-1 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t3 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct pcr_t3 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.pcr_t3 + Is Table Level Stats: true + +PREHOOK: query: from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Output: default@pcr_t2 +PREHOOK: Output: default@pcr_t3 +POSTHOOK: query: from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Output: default@pcr_t2 +POSTHOOK: Output: default@pcr_t3 +POSTHOOK: Lineage: pcr_t2.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: pcr_t2.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: pcr_t3.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: pcr_t3.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain extended +from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Output: default@pcr_t2 +PREHOOK: Output: default@pcr_t3 +POSTHOOK: query: explain extended +from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Output: default@pcr_t2 +POSTHOOK: Output: default@pcr_t3 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 2) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 2 (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t2 + numFiles 1 + numRows 20 + rawDataSize 160 + serialization.ddl struct pcr_t2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: 2 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Filter Operator + isSamplingPred: false + predicate: (key = 3) (type: boolean) + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 3 (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 2 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t3 + numFiles 1 + numRows 20 + rawDataSize 160 + serialization.ddl struct pcr_t3 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t3 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: 3 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds=2000-04-08 [pcr_t1] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Reducer 3 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t2 + numFiles 1 + numRows 20 + rawDataSize 160 + serialization.ddl struct pcr_t2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2 + + Stage: Stage-4 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.pcr_t2 + Is Table Level Stats: true + + Stage: Stage-1 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t3 + numFiles 1 + numRows 20 + rawDataSize 160 + serialization.ddl struct pcr_t3 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t3 + + Stage: Stage-5 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.pcr_t3 + Is Table Level Stats: true + +PREHOOK: query: from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1 +PREHOOK: Input: default@pcr_t1@ds=2000-04-08 +PREHOOK: Output: default@pcr_t2 +PREHOOK: Output: default@pcr_t3 +POSTHOOK: query: from pcr_t1 +insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 +insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 +POSTHOOK: Output: default@pcr_t2 +POSTHOOK: Output: default@pcr_t3 +POSTHOOK: Lineage: pcr_t2.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: pcr_t2.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: pcr_t3.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: pcr_t3.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain extended select key, value from srcpart where ds='2008-04-08' and hr=11 order by key limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value from srcpart where ds='2008-04-08' and hr=11 order by key limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value` +FROM `default`.`srcpart` +WHERE `ds` = '2008-04-08' AND `hr` = 11 +ORDER BY `key` +LIMIT 10 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Top N Key Operator + sort order: + + keys: key (type: string) + null sort order: z + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 10 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + TopN: 10 + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: select key, value from srcpart where ds='2008-04-04' and hr=11 order by key limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +#### A masked pattern was here #### +POSTHOOK: query: select key, value from srcpart where ds='2008-04-04' and hr=11 order by key limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +#### A masked pattern was here #### +PREHOOK: query: explain extended select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` +FROM (SELECT `key`, `value`, `hr` +FROM `default`.`srcpart` +WHERE `key` = 11 AND `hr` IN ('11', '12') AND `ds` = '2008-04-08' +ORDER BY `key`, `hr`) AS `t1` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ((UDFToDouble(key) = 11.0D) and (hr) IN ('11', '12') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (UDFToDouble(key) = 11.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +11 val_11 2008-04-08 11 +11 val_11 2008-04-08 12 +PREHOOK: query: explain extended select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds`, CAST('11' AS STRING) AS `hr` +FROM (SELECT `key`, `value`, `ds` +FROM `default`.`srcpart` +WHERE `key` = 11 AND `hr` = '11' +ORDER BY `key`, `ds`) AS `t1` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ((UDFToDouble(key) = 11.0D) and (hr = '11')) (type: boolean) + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (UDFToDouble(key) = 11.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 224000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 224000 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +11 val_11 2008-04-08 11 +11 val_11 2008-04-09 11 +PREHOOK: query: drop table pcr_t1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t1 +PREHOOK: Output: default@pcr_t1 +POSTHOOK: query: drop table pcr_t1 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Output: default@pcr_t1 +PREHOOK: query: drop table pcr_t2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t2 +PREHOOK: Output: default@pcr_t2 +POSTHOOK: query: drop table pcr_t2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t2 +POSTHOOK: Output: default@pcr_t2 +PREHOOK: query: drop table pcr_t3 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t3 +PREHOOK: Output: default@pcr_t3 +POSTHOOK: query: drop table pcr_t3 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t3 +POSTHOOK: Output: default@pcr_t3 +PREHOOK: query: drop table pcr_foo +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_foo +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table pcr_foo (key int, value string) partitioned by (ds int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_foo +POSTHOOK: query: create table pcr_foo (key int, value string) partitioned by (ds int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_foo +PREHOOK: query: insert overwrite table pcr_foo partition (ds=3) select * from src where key < 10 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_foo@ds=3 +POSTHOOK: query: insert overwrite table pcr_foo partition (ds=3) select * from src where key < 10 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_foo@ds=3 +POSTHOOK: Lineage: pcr_foo PARTITION(ds=3).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_foo PARTITION(ds=3).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_foo partition (ds=5) select * from src where key < 10 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_foo@ds=5 +POSTHOOK: query: insert overwrite table pcr_foo partition (ds=5) select * from src where key < 10 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_foo@ds=5 +POSTHOOK: Lineage: pcr_foo PARTITION(ds=5).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_foo PARTITION(ds=5).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_foo partition (ds=7) select * from src where key < 10 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_foo@ds=7 +POSTHOOK: query: insert overwrite table pcr_foo partition (ds=7) select * from src where key < 10 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_foo@ds=7 +POSTHOOK: Lineage: pcr_foo PARTITION(ds=7).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_foo PARTITION(ds=7).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select key, value, ds from pcr_foo where (ds % 2 == 1) +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_foo +PREHOOK: Input: default@pcr_foo@ds=3 +PREHOOK: Input: default@pcr_foo@ds=5 +PREHOOK: Input: default@pcr_foo@ds=7 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_foo where (ds % 2 == 1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_foo +POSTHOOK: Input: default@pcr_foo@ds=3 +POSTHOOK: Input: default@pcr_foo@ds=5 +POSTHOOK: Input: default@pcr_foo@ds=7 +#### A masked pattern was here #### +0 val_0 3 +0 val_0 3 +0 val_0 3 +2 val_2 3 +4 val_4 3 +5 val_5 3 +5 val_5 3 +5 val_5 3 +8 val_8 3 +9 val_9 3 +0 val_0 5 +0 val_0 5 +0 val_0 5 +2 val_2 5 +4 val_4 5 +5 val_5 5 +5 val_5 5 +5 val_5 5 +8 val_8 5 +9 val_9 5 +0 val_0 7 +0 val_0 7 +0 val_0 7 +2 val_2 7 +4 val_4 7 +5 val_5 7 +5 val_5 7 +5 val_5 7 +8 val_8 7 +9 val_9 7 +PREHOOK: query: select key, value, ds from pcr_foo where (ds / 3 < 2) +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_foo +PREHOOK: Input: default@pcr_foo@ds=3 +PREHOOK: Input: default@pcr_foo@ds=5 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from pcr_foo where (ds / 3 < 2) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_foo +POSTHOOK: Input: default@pcr_foo@ds=3 +POSTHOOK: Input: default@pcr_foo@ds=5 +#### A masked pattern was here #### +0 val_0 3 +0 val_0 3 +0 val_0 3 +2 val_2 3 +4 val_4 3 +5 val_5 3 +5 val_5 3 +5 val_5 3 +8 val_8 3 +9 val_9 3 +0 val_0 5 +0 val_0 5 +0 val_0 5 +2 val_2 5 +4 val_4 5 +5 val_5 5 +5 val_5 5 +5 val_5 5 +8 val_8 5 +9 val_9 5 +PREHOOK: query: drop table pcr_foo +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_foo +PREHOOK: Output: default@pcr_foo +POSTHOOK: query: drop table pcr_foo +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_foo +POSTHOOK: Output: default@pcr_foo +PREHOOK: query: create table ab(strct struct) +row format delimited + fields terminated by '\t' + collection items terminated by '\001' +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ab +POSTHOOK: query: create table ab(strct struct) +row format delimited + fields terminated by '\t' + collection items terminated by '\001' +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ab +PREHOOK: query: load data local inpath '../../data/files/kv1.txt' +overwrite into table ab +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@ab +POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' +overwrite into table ab +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@ab +PREHOOK: query: drop table foo_field +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table foo_field +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table foo_field (s struct) partitioned by (ds int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@foo_field +POSTHOOK: query: create table foo_field (s struct) partitioned by (ds int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@foo_field +PREHOOK: query: insert overwrite table foo_field partition (ds=5) select strct from ab where strct.a < 10 limit 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@ab +PREHOOK: Output: default@foo_field@ds=5 +POSTHOOK: query: insert overwrite table foo_field partition (ds=5) select strct from ab where strct.a < 10 limit 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ab +POSTHOOK: Output: default@foo_field@ds=5 +POSTHOOK: Lineage: foo_field PARTITION(ds=5).s SIMPLE [(ab)ab.FieldSchema(name:strct, type:struct, comment:null), ] +PREHOOK: query: insert overwrite table foo_field partition (ds=7) select strct from ab where strct.a > 190 limit 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@ab +PREHOOK: Output: default@foo_field@ds=7 +POSTHOOK: query: insert overwrite table foo_field partition (ds=7) select strct from ab where strct.a > 190 limit 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ab +POSTHOOK: Output: default@foo_field@ds=7 +POSTHOOK: Lineage: foo_field PARTITION(ds=7).s SIMPLE [(ab)ab.FieldSchema(name:strct, type:struct, comment:null), ] +PREHOOK: query: select s,ds from foo_field where ((ds + s.a) > 0) order by ds,s +PREHOOK: type: QUERY +PREHOOK: Input: default@foo_field +PREHOOK: Input: default@foo_field@ds=5 +PREHOOK: Input: default@foo_field@ds=7 +#### A masked pattern was here #### +POSTHOOK: query: select s,ds from foo_field where ((ds + s.a) > 0) order by ds,s +POSTHOOK: type: QUERY +POSTHOOK: Input: default@foo_field +POSTHOOK: Input: default@foo_field@ds=5 +POSTHOOK: Input: default@foo_field@ds=7 +#### A masked pattern was here #### +{"a":0,"b":"val_0"} 5 +{"a":4,"b":"val_4"} 5 +{"a":238,"b":"val_238"} 7 +{"a":311,"b":"val_311"} 7 +PREHOOK: query: drop table foo_field +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@foo_field +PREHOOK: Output: default@foo_field +POSTHOOK: query: drop table foo_field +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@foo_field +POSTHOOK: Output: default@foo_field +PREHOOK: query: explain select key,value from srcpart where cast(hr as double) = cast(11 as double) +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: explain select key,value from srcpart where cast(hr as double) = cast(11 as double) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + filterExpr: (11.0D = 11.0D) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: explain select key,value from srcpart where hr = cast(11 as double) +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: explain select key,value from srcpart where hr = cast(11 as double) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + filterExpr: (11.0D = 11.0D) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: explain select key,value from srcpart where cast(hr as double) = 11 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: explain select key,value from srcpart where cast(hr as double) = 11 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + filterExpr: (11.0D = 11.0D) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + diff --git ql/src/test/results/clientpositive/pcs.q.out ql/src/test/results/clientpositive/llap/pcs.q.out similarity index 63% rename from ql/src/test/results/clientpositive/pcs.q.out rename to ql/src/test/results/clientpositive/llap/pcs.q.out index 1b7e3da922..9a1d5a5362 100644 --- ql/src/test/results/clientpositive/pcs.q.out +++ ql/src/test/results/clientpositive/llap/pcs.q.out @@ -108,163 +108,172 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcs_t1 + filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcs_t1 + name: default.pcs_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcs_t1 + name: default.pcs_t1 + Truncated Path -> Alias: + /pcs_t1/ds=2000-04-08 [pcs_t1] + /pcs_t1/ds=2000-04-09 [pcs_t1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string), ds (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcs_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcs_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcs_t1 - name: default.pcs_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcs_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.pcs_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcs_t1 - name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [pcs_t1] - /pcs_t1/ds=2000-04-09 [pcs_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -301,57 +310,14 @@ OPTIMIZED SQL: SELECT `ds` FROM `default`.`pcs_t1` WHERE ROW(`key`, `ds`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: ds=2000-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -397,9 +363,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -445,15 +409,18 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [pcs_t1] - /pcs_t1/ds=2000-04-09 [pcs_t1] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: pcs_t1 + filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: select ds from pcs_t1 where struct(ds, key) in (struct('2000-04-08',1), struct('2000-04-09',2)) PREHOOK: type: QUERY @@ -484,57 +451,14 @@ OPTIMIZED SQL: SELECT `ds` FROM `default`.`pcs_t1` WHERE ROW(`ds`, `key` + 2) IN (ROW('2000-04-08', 3), ROW('2000-04-09', 4)) STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - filterExpr: ((struct(ds,(key + 2))) IN (const struct('2000-04-08',3), const struct('2000-04-09',4)) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(ds,(key + 2))) IN (const struct('2000-04-08',3), const struct('2000-04-09',4)) (type: boolean) - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: ds=2000-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -580,9 +504,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -628,15 +550,18 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [pcs_t1] - /pcs_t1/ds=2000-04-09 [pcs_t1] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: pcs_t1 + filterExpr: ((struct(ds,(key + 2))) IN (const struct('2000-04-08',3), const struct('2000-04-09',4)) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(ds,(key + 2))) IN (const struct('2000-04-08',3), const struct('2000-04-09',4)) (type: boolean) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: select ds from pcs_t1 where struct(ds, key+2) in (struct('2000-04-08',3), struct('2000-04-09',4)) PREHOOK: type: QUERY @@ -669,196 +594,326 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key) IN (1, 2) and (ds) IN ('2000-04-08', '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), ds (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col1 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: int) - auto parallelism: false - TableScan - alias: b - filterExpr: (ds) IN ('2000-04-09', '2000-04-08') (type: boolean) - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), ds (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col1 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: int) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcs_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcs_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcs_t1 - name: default.pcs_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcs_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), ds (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col1 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 6 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: int) + auto parallelism: true + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.6666666 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + Dynamic Partitioning Event Operator + Target column: ds (string) + Target Input: b + Partition key expr: ds + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + Target Vertex: Map 3 + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcs_t1 + name: default.pcs_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### - name default.pcs_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcs_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcs_t1 + name: default.pcs_t1 + Truncated Path -> Alias: + /pcs_t1/ds=2000-04-08 [a] + /pcs_t1/ds=2000-04-09 [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: (ds) IN ('2000-04-09', '2000-04-08') (type: boolean) + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), ds (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col1 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: int) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcs_t1 - name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [$hdt$_0:a, $hdt$_1:b] - /pcs_t1/ds=2000-04-09 [$hdt$_0:a, $hdt$_1:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 120 Data size: 45120 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: (struct(_col0,_col1,_col3)) IN (const struct(1,'2000-04-08','2000-04-09'), const struct(2,'2000-04-09','2000-04-08')) (type: boolean) - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcs_t1 + name: default.pcs_t1 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcs_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: - bucketing_version -1 - columns _col0,_col1 - columns.types string:int - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcs_t1 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcs_t1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + name: default.pcs_t1 + name: default.pcs_t1 + Truncated Path -> Alias: + /pcs_t1/ds=2000-04-08 [b] + /pcs_t1/ds=2000-04-09 [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 1 + residual filter predicates: {(struct(_col0,_col1,_col3)) IN (const struct(1,'2000-04-08','2000-04-09'), const struct(2,'2000-04-09','2000-04-08'))} + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types string:int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -894,57 +949,14 @@ OPTIMIZED SQL: SELECT `ds` FROM `default`.`pcs_t1` WHERE ROW(`ds`, `key` + `key`) IN (ROW('2000-04-08', 1), ROW('2000-04-09', 2)) STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - filterExpr: ((struct(ds,(key + key))) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(ds,(key + key))) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: ds=2000-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -990,9 +1002,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1038,15 +1048,18 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [pcs_t1] - /pcs_t1/ds=2000-04-09 [pcs_t1] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: pcs_t1 + filterExpr: ((struct(ds,(key + key))) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(ds,(key + key))) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: select ds from pcs_t1 where struct(ds, key+key) in (struct('2000-04-08',1), struct('2000-04-09',2)) PREHOOK: type: QUERY @@ -1080,59 +1093,68 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: int) - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: lag_window_0 - arguments: _col0 - name: lag - window function: GenericUDAFLagEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 20 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: lag_window_0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcs_t1 + filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: lag_window_0 + arguments: _col0 + name: lag + window function: GenericUDAFLagEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 20 Data size: 9120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: lag_window_0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1183,86 +1205,100 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - TableScan - alias: y - filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 4 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: unknown + Map 4 + Map Operator Tree: + TableScan + alias: y + filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: unknown + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2008-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2008-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Union 2 + Vertex: Union 2 Stage: Stage-0 Fetch Operator @@ -1361,12 +1397,10 @@ STAGE PLANS: TableScan alias: pcs_t1 filterExpr: (ds = '2000-04-08') (type: boolean) - Statistics: Num rows: 20 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator expressions: '2000-04-08' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select ds from pcs_t1 where struct(case when ds='2000-04-08' then 10 else 20 end) in (struct(10),struct(11)) @@ -1415,56 +1449,14 @@ OPTIMIZED SQL: SELECT `ds` FROM `default`.`pcs_t1` WHERE ROW(`ds`, `key`, RAND(100)) IN (ROW('2000-04-08', 1, 0.2), ROW('2000-04-09', 2, 0.3)) STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - Statistics: Num rows: 40 Data size: 7520 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(ds,key,rand(100))) IN (const struct('2000-04-08',1,0.2D), const struct('2000-04-09',2,0.3D)) (type: boolean) - Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: ds=2000-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1510,9 +1502,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1558,15 +1548,17 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [pcs_t1] - /pcs_t1/ds=2000-04-09 [pcs_t1] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: pcs_t1 + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(ds,key,rand(100))) IN (const struct('2000-04-08',1,0.2D), const struct('2000-04-09',2,0.3D)) (type: boolean) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: explain extended select ds from pcs_t1 where struct(ds='2000-04-08' or key = 2, key) in (struct(true,2), struct(false,3)) PREHOOK: type: QUERY @@ -1586,57 +1578,14 @@ OPTIMIZED SQL: SELECT `ds` FROM `default`.`pcs_t1` WHERE `ds` <> '2000-04-08' AND `key` <> 2 AND `key` = 3 OR (`ds` = '2000-04-08' OR `key` IS NOT NULL) AND `key` = 2 STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - filterExpr: (((ds <> '2000-04-08') and (key <> 2) and (key = 3)) or (((ds = '2000-04-08') or key is not null) and (key = 2))) (type: boolean) - Statistics: Num rows: 60 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds <> '2000-04-08') and (key <> 2) and (key = 3)) or (((ds = '2000-04-08') or key is not null) and (key = 2))) (type: boolean) - Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: ds=2000-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1682,9 +1631,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1730,9 +1677,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-10 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1778,16 +1723,18 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [pcs_t1] - /pcs_t1/ds=2000-04-09 [pcs_t1] - /pcs_t1/ds=2000-04-10 [pcs_t1] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: pcs_t1 + filterExpr: (((ds <> '2000-04-08') and (key <> 2) and (key = 3)) or (((ds = '2000-04-08') or key is not null) and (key = 2))) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds <> '2000-04-08') and (key <> 2) and (key = 3)) or (((ds = '2000-04-08') or key is not null) and (key = 2))) (type: boolean) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: select ds from pcs_t1 where struct(ds='2000-04-08' or key = 2, key) in (struct(true,2), struct(false,3)) PREHOOK: type: QUERY @@ -1824,57 +1771,14 @@ OPTIMIZED SQL: SELECT `ds` FROM `default`.`pcs_t1` WHERE `key` = 3 OR ((`ds` = '2000-04-08' OR `key` IS NOT NULL) AND `key` = 2 OR `ds` <> '2000-04-08' AND `key` <> 2 AND `key` = 3) AND `key` + 5 > 0 STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcs_t1 - filterExpr: ((key = 3) or (((((ds = '2000-04-08') or key is not null) and (key = 2)) or ((ds <> '2000-04-08') and (key <> 2) and (key = 3))) and ((key + 5) > 0))) (type: boolean) - Statistics: Num rows: 60 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key = 3) or (((((ds = '2000-04-08') or key is not null) and (key = 2)) or ((ds <> '2000-04-08') and (key <> 2) and (key = 3))) and ((key + 5) > 0))) (type: boolean) - Statistics: Num rows: 8 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 8 Data size: 1472 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: ds=2000-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1920,9 +1824,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -1968,9 +1870,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 -#### A masked pattern was here #### Partition - base file name: ds=2000-04-10 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -2016,16 +1916,18 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.pcs_t1 name: default.pcs_t1 - Truncated Path -> Alias: - /pcs_t1/ds=2000-04-08 [pcs_t1] - /pcs_t1/ds=2000-04-09 [pcs_t1] - /pcs_t1/ds=2000-04-10 [pcs_t1] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: pcs_t1 + filterExpr: ((key = 3) or (((((ds = '2000-04-08') or key is not null) and (key = 2)) or ((ds <> '2000-04-08') and (key <> 2) and (key = 3))) and ((key + 5) > 0))) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 3) or (((((ds = '2000-04-08') or key is not null) and (key = 2)) or ((ds <> '2000-04-08') and (key <> 2) and (key = 3))) and ((key + 5) > 0))) (type: boolean) + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: select ds from pcs_t1 where key = 3 or (struct(ds='2000-04-08' or key = 2, key) in (struct(true,2), struct(false,3)) and key+5 > 0) PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/pointlookup.q.out ql/src/test/results/clientpositive/llap/pointlookup.q.out similarity index 64% rename from ql/src/test/results/clientpositive/pointlookup.q.out rename to ql/src/test/results/clientpositive/llap/pointlookup.q.out index a128626231..d4aef2f7a8 100644 --- ql/src/test/results/clientpositive/pointlookup.q.out +++ ql/src/test/results/clientpositive/llap/pointlookup.q.out @@ -35,38 +35,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key = '0') and (value = 'val_0')) or ((key = '1') and (value = 'val_1')) or ((key = '2') and (value = 'val_2')) or ((key = '3') and (value = 'val_3')) or ((key = '4') and (value = 'val_4')) or ((key = '5') and (value = 'val_5')) or ((key = '6') and (value = 'val_6')) or ((key = '7') and (value = 'val_7')) or ((key = '8') and (value = 'val_8')) or ((key = '9') and (value = 'val_9')) or ((key = '10') and (value = 'val_10'))) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key = '0') and (value = 'val_0')) or ((key = '1') and (value = 'val_1')) or ((key = '2') and (value = 'val_2')) or ((key = '3') and (value = 'val_3')) or ((key = '4') and (value = 'val_4')) or ((key = '5') and (value = 'val_5')) or ((key = '6') and (value = 'val_6')) or ((key = '7') and (value = 'val_7')) or ((key = '8') and (value = 'val_8')) or ((key = '9') and (value = 'val_9')) or ((key = '10') and (value = 'val_10'))) (type: boolean) - Statistics: Num rows: 11 Data size: 1958 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: (((key = '0') and (value = 'val_0')) or ((key = '1') and (value = 'val_1')) or ((key = '2') and (value = 'val_2')) or ((key = '3') and (value = 'val_3')) or ((key = '4') and (value = 'val_4')) or ((key = '5') and (value = 'val_5')) or ((key = '6') and (value = 'val_6')) or ((key = '7') and (value = 'val_7')) or ((key = '8') and (value = 'val_8')) or ((key = '9') and (value = 'val_9')) or ((key = '10') and (value = 'val_10'))) (type: boolean) + Filter Operator + predicate: (((key = '0') and (value = 'val_0')) or ((key = '1') and (value = 'val_1')) or ((key = '2') and (value = 'val_2')) or ((key = '3') and (value = 'val_3')) or ((key = '4') and (value = 'val_4')) or ((key = '5') and (value = 'val_5')) or ((key = '6') and (value = 'val_6')) or ((key = '7') and (value = 'val_7')) or ((key = '8') and (value = 'val_8')) or ((key = '9') and (value = 'val_9')) or ((key = '10') and (value = 'val_10'))) (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: create table orOutput as SELECT key @@ -144,38 +128,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) + Filter Operator + predicate: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: create table inOutput as SELECT key @@ -253,38 +221,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) + Filter Operator + predicate: (struct(key,value)) IN (const struct('0','val_0'), const struct('1','val_1'), const struct('2','val_2'), const struct('3','val_3'), const struct('4','val_4'), const struct('5','val_5'), const struct('6','val_6'), const struct('7','val_7'), const struct('8','val_8'), const struct('9','val_9'), const struct('10','val_10')) (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: create table inOutputOpt as SELECT key @@ -352,7 +304,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@inoutputopt #### A masked pattern was here #### 11 -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select orOutput.key, inOutput.key from orOutput full outer join inOutput on (orOutput.key = inOutput.key) where orOutput.key = null @@ -369,7 +321,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@inoutput POSTHOOK: Input: default@oroutput #### A masked pattern was here #### -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select orOutput.key, inOutputOpt.key from orOutput full outer join inOutputOpt on (orOutput.key = inOutputOpt.key) where orOutput.key = null diff --git ql/src/test/results/clientpositive/llap/pointlookup2.q.out ql/src/test/results/clientpositive/llap/pointlookup2.q.out new file mode 100644 index 0000000000..01fadb3c62 --- /dev/null +++ ql/src/test/results/clientpositive/llap/pointlookup2.q.out @@ -0,0 +1,3272 @@ +PREHOOK: query: drop table pcr_t1_n2 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t1_n2 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table pcr_t2_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t2_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table pcr_t3 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t3 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table pcr_t1_n2 (key int, value string) partitioned by (ds string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t1_n2 +POSTHOOK: query: create table pcr_t1_n2 (key int, value string) partitioned by (ds string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t1_n2 +PREHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-08') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-08') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-09') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-09') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-10') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n2@ds=2000-04-10 +POSTHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-10') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n2@ds=2000-04-10 +POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: create table pcr_t2_n0 (ds string, key int, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t2_n0 +POSTHOOK: query: create table pcr_t2_n0 (ds string, key int, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t2_n0 +PREHOOK: query: from pcr_t1_n2 +insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Output: default@pcr_t2_n0 +POSTHOOK: query: from pcr_t1_n2 +insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Output: default@pcr_t2_n0 +POSTHOOK: Lineage: pcr_t2_n0.ds SIMPLE [] +POSTHOOK: Lineage: pcr_t2_n0.key SIMPLE [(pcr_t1_n2)pcr_t1_n2.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: pcr_t2_n0.value SIMPLE [(pcr_t1_n2)pcr_t1_n2.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: from pcr_t1_n2 +insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' and key=2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Output: default@pcr_t2_n0 +POSTHOOK: query: from pcr_t1_n2 +insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' and key=2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Output: default@pcr_t2_n0 +POSTHOOK: Lineage: pcr_t2_n0.ds SIMPLE [] +POSTHOOK: Lineage: pcr_t2_n0.key SIMPLE [] +POSTHOOK: Lineage: pcr_t2_n0.value SIMPLE [(pcr_t1_n2)pcr_t1_n2.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain extended +select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' AND `key` = 1 OR `ds` = '2000-04-09' AND `key` = 2 +ORDER BY `key`, `value`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n2 + filterExpr: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [pcr_t1_n2] + /pcr_t1_n2/ds=2000-04-09 [pcr_t1_n2] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t0`.`key`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' +order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' +order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t0`.`key`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-09 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t0`.`ds`, `t2`.`ds` AS `ds1`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` +FROM (SELECT `key`, `value`, `ds`, `ds` = '2000-04-08' AS `=`, `ds` = '2000-04-09' AS `=7` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' OR `ds` = '2000-04-09') AS `t0` +INNER JOIN (SELECT `ds`, `key`, `value`, `key` = 1 AS `=`, `key` = 2 AS `=7` +FROM `default`.`pcr_t2_n0` +WHERE `key` = 1 OR `key` = 2) AS `t2` ON `t0`.`=` AND `t2`.`=` OR `t0`.`=7` AND `t2`.`=7` +ORDER BY `t2`.`key`, `t2`.`value`, `t0`.`ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), value (type: string), ds (type: string), (ds = '2000-04-08') (type: boolean), (ds = '2000-04-09') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 40 Data size: 11440 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 40 Data size: 11440 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + /pcr_t1_n2/ds=2000-04-09 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: ((key = 1) or (key = 2)) (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) or (key = 2)) (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ds (type: string), key (type: int), value (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: pcr_t2_n0 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2_n0 + name: default.pcr_t2_n0 + Truncated Path -> Alias: + /pcr_t2_n0 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Position of Big Table: 0 + residual filter predicates: {((_col3 and _col8) or (_col4 and _col9))} + Statistics: Num rows: 20 Data size: 9620 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:string:int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t0`.`ds`, `t2`.`ds` AS `ds1`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` +FROM (SELECT `key`, `value`, `ds`, `key` = 1 AS `=`, `key` = 2 AS `=7` +FROM `default`.`pcr_t1_n2` +WHERE `key` = 1 OR `key` = 2) AS `t0` +INNER JOIN (SELECT `ds`, `key`, `value`, `ds` = '2000-04-08' AS `=`, `ds` = '2000-04-09' AS `=7` +FROM `default`.`pcr_t2_n0` +WHERE `ds` = '2000-04-08' OR `ds` = '2000-04-09') AS `t2` ON `t2`.`=` AND `t0`.`=` OR `t2`.`=7` AND `t0`.`=7` +ORDER BY `t0`.`key`, `t0`.`value`, `t2`.`ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: ((key = 1) or (key = 2)) (type: boolean) + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) or (key = 2)) (type: boolean) + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 10 Data size: 2860 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 10 Data size: 2860 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + /pcr_t1_n2/ds=2000-04-09 [t1] + /pcr_t1_n2/ds=2000-04-10 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ds (type: string), key (type: int), value (type: string), (ds = '2000-04-08') (type: boolean), (ds = '2000-04-09') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: pcr_t2_n0 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2_n0 + name: default.pcr_t2_n0 + Truncated Path -> Alias: + /pcr_t2_n0 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Position of Big Table: 0 + residual filter predicates: {((_col8 and _col3) or (_col9 and _col4))} + Statistics: Num rows: 4 Data size: 1924 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:string:int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +2 val_2 2000-04-09 +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +2 val_2 2000-04-08 2 val_2 2000-04-08 +4 val_4 2000-04-08 4 val_4 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +8 val_8 2000-04-08 8 val_8 2000-04-08 +9 val_9 2000-04-08 9 val_9 2000-04-08 +10 val_10 2000-04-08 10 val_10 2000-04-08 +11 val_11 2000-04-08 11 val_11 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +17 val_17 2000-04-08 17 val_17 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +19 val_19 2000-04-08 19 val_19 2000-04-08 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +9 val_9 2000-04-09 2000-04-08 2 val_2 +8 val_8 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +4 val_4 2000-04-09 2000-04-08 2 val_2 +2 val_2 2000-04-09 2000-04-08 2 val_2 +19 val_19 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +17 val_17 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +11 val_11 2000-04-09 2000-04-08 2 val_2 +10 val_10 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +9 val_9 2000-04-09 2000-04-08 2 val_2 +8 val_8 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +4 val_4 2000-04-09 2000-04-08 2 val_2 +2 val_2 2000-04-09 2000-04-08 2 val_2 +19 val_19 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +17 val_17 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +11 val_11 2000-04-09 2000-04-08 2 val_2 +10 val_10 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +PREHOOK: query: explain extended +select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`pcr_t1_n2` +WHERE ROW(`key`, `ds`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) +ORDER BY `key`, `value`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n2 + filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [pcr_t1_n2] + /pcr_t1_n2/ds=2000-04-09 [pcr_t1_n2] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t0`.`key`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' +order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' +order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`pcr_t1_n2` +WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t0`.`key`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-09 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + /pcr_t1_n2/ds=2000-04-09 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ds (type: string), key (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: pcr_t2_n0 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2_n0 + name: default.pcr_t2_n0 + Truncated Path -> Alias: + /pcr_t2_n0 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Position of Big Table: 0 + residual filter predicates: {(struct(_col2,_col4)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2))} + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:string:int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n2 + partition_columns ds + partition_columns.types string + serialization.ddl struct pcr_t1_n2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n2 + name: default.pcr_t1_n2 + Truncated Path -> Alias: + /pcr_t1_n2/ds=2000-04-08 [t1] + /pcr_t1_n2/ds=2000-04-09 [t1] + /pcr_t1_n2/ds=2000-04-10 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ds (type: string), key (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: pcr_t2_n0 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns ds,key,value + columns.comments + columns.types string:int:string +#### A masked pattern was here #### + name default.pcr_t2_n0 + numFiles 1 + numRows 1 + rawDataSize 18 + serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 19 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t2_n0 + name: default.pcr_t2_n0 + Truncated Path -> Alias: + /pcr_t2_n0 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Position of Big Table: 0 + residual filter predicates: {(struct(_col0,_col3)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09'))} + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int:string:string:string:int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds +from pcr_t1_n2 +where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) +order by key, value, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +#### A masked pattern was here #### +2 val_2 2000-04-09 +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t1_n2 t2 +on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' +order by t1.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +#### A masked pattern was here #### +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +0 val_0 2000-04-08 0 val_0 2000-04-08 +2 val_2 2000-04-08 2 val_2 2000-04-08 +4 val_4 2000-04-08 4 val_4 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +5 val_5 2000-04-08 5 val_5 2000-04-08 +8 val_8 2000-04-08 8 val_8 2000-04-08 +9 val_9 2000-04-08 9 val_9 2000-04-08 +10 val_10 2000-04-08 10 val_10 2000-04-08 +11 val_11 2000-04-08 11 val_11 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +12 val_12 2000-04-08 12 val_12 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +15 val_15 2000-04-08 15 val_15 2000-04-08 +17 val_17 2000-04-08 17 val_17 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +18 val_18 2000-04-08 18 val_18 2000-04-08 +19 val_19 2000-04-08 19 val_19 2000-04-08 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +9 val_9 2000-04-09 2000-04-08 2 val_2 +8 val_8 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +4 val_4 2000-04-09 2000-04-08 2 val_2 +2 val_2 2000-04-09 2000-04-08 2 val_2 +19 val_19 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +17 val_17 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +11 val_11 2000-04-09 2000-04-08 2 val_2 +10 val_10 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +9 val_9 2000-04-09 2000-04-08 2 val_2 +8 val_8 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +5 val_5 2000-04-09 2000-04-08 2 val_2 +4 val_4 2000-04-09 2000-04-08 2 val_2 +2 val_2 2000-04-09 2000-04-08 2 val_2 +19 val_19 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +18 val_18 2000-04-09 2000-04-08 2 val_2 +17 val_17 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +15 val_15 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +12 val_12 2000-04-09 2000-04-08 2 val_2 +11 val_11 2000-04-09 2000-04-08 2 val_2 +10 val_10 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +0 val_0 2000-04-09 2000-04-08 2 val_2 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +PREHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n2 t1 join pcr_t2_n0 t2 +where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) +order by t1.key, t1.value, t2.ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 +POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 +POSTHOOK: Input: default@pcr_t2_n0 +#### A masked pattern was here #### +PREHOOK: query: drop table pcr_t1_n2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t1_n2 +PREHOOK: Output: default@pcr_t1_n2 +POSTHOOK: query: drop table pcr_t1_n2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t1_n2 +POSTHOOK: Output: default@pcr_t1_n2 +PREHOOK: query: drop table pcr_t2_n0 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t2_n0 +PREHOOK: Output: default@pcr_t2_n0 +POSTHOOK: query: drop table pcr_t2_n0 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t2_n0 +POSTHOOK: Output: default@pcr_t2_n0 +PREHOOK: query: drop table pcr_t3 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t3 +POSTHOOK: type: DROPTABLE diff --git ql/src/test/results/clientpositive/llap/pointlookup3.q.out ql/src/test/results/clientpositive/llap/pointlookup3.q.out new file mode 100644 index 0000000000..d945be2023 --- /dev/null +++ ql/src/test/results/clientpositive/llap/pointlookup3.q.out @@ -0,0 +1,3110 @@ +PREHOOK: query: drop table pcr_t1_n1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t1_n1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table pcr_t1_n1 (key int, value string) partitioned by (ds1 string, ds2 string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t1_n1 +POSTHOOK: query: create table pcr_t1_n1 (key int, value string) partitioned by (ds1 string, ds2 string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t1_n1 +PREHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-08,ds2=2001-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-08,ds2=2001-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-09,ds2=2001-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-09,ds2=2001-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +POSTHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-10,ds2=2001-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-10,ds2=2001-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-08' AND `key` = 1 OR `ds1` = '2000-04-09' AND `key` = 2 +ORDER BY `key`, `value`, `ds1`, `ds2` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n1 + filterExpr: (((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n1] + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, CAST('2001-04-08' AS STRING) AS `ds2` +FROM (SELECT `key`, `value`, `ds1` +FROM `default`.`pcr_t1_n1` +WHERE (`ds1` = '2000-04-08' AND `key` = 1 OR `ds1` = '2000-04-09' AND `key` = 2) AND `ds2` = '2001-04-08' +ORDER BY `key`, `value`, `ds1`) AS `t1` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n1 + filterExpr: ((((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) and (ds2 = '2001-04-08')) (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 1) (type: boolean) + Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, `t3`.`ds1` AS `ds11`, CAST('2001-04-08' AS STRING) AS `ds21` +FROM (SELECT * +FROM (SELECT `key`, `value`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value`, `ds1` +FROM `default`.`pcr_t1_n1` +WHERE `ds2` = '2001-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col3 (type: int), _col4 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), '2001-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds11`, `t3`.`ds20` AS `ds21` +FROM (SELECT * +FROM (SELECT `key`, `value`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col3 (type: int), _col4 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2000-04-09' (type: string), VALUE._col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t0`.`ds1`, `t0`.`ds2`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1`, `t2`.`ds1` AS `ds11`, `t2`.`ds2` AS `ds21` +FROM (SELECT `key`, `value`, `ds1`, `ds2`, `ds1` = '2000-04-08' AS `=`, `ds1` = '2000-04-09' AS `=8` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-08' OR `ds1` = '2000-04-09') AS `t0` +INNER JOIN (SELECT `key`, `value`, `ds1`, `ds2`, `key` = 1 AS `=`, `key` = 2 AS `=8` +FROM `default`.`pcr_t1_n1` +WHERE `key` = 1 OR `key` = 2) AS `t2` ON `t0`.`=` AND `t2`.`=` OR `t0`.`=8` AND `t2`.`=8` +ORDER BY `t2`.`key`, `t2`.`value`, `t0`.`ds1` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: ((ds1 = '2000-04-08') or (ds1 = '2000-04-09')) (type: boolean) + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string), (ds1 = '2000-04-08') (type: boolean), (ds1 = '2000-04-09') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 40 Data size: 18800 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 40 Data size: 18800 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: boolean), _col5 (type: boolean) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t1] + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: ((key = 1) or (key = 2)) (type: boolean) + Statistics: Num rows: 60 Data size: 27720 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 1) or (key = 2)) (type: boolean) + Statistics: Num rows: 10 Data size: 4620 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 10 Data size: 4700 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 10 Data size: 4700 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: boolean), _col5 (type: boolean) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-10 + ds2 2001-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t2] + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [t2] + /pcr_t1_n1/ds1=2000-04-10/ds2=2001-04-10 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Position of Big Table: 0 + residual filter predicates: {((_col4 and _col10) or (_col5 and _col11))} + Statistics: Num rows: 200 Data size: 188000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string), _col9 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +2 val_2 2000-04-09 2001-04-09 +PREHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +PREHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-08 2001-04-08 +4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-08 2001-04-08 +9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-08 2001-04-08 +10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-08 2001-04-08 +11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-08 2001-04-08 +PREHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-09 2001-04-09 +4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-09 2001-04-09 +9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-09 2001-04-09 +10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-09 2001-04-09 +11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-09 2001-04-09 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE ROW(`key`, `ds1`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) +ORDER BY `key`, `value`, `ds1`, `ds2` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n1 + filterExpr: ((struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds1)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n1] + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, CAST('2001-04-08' AS STRING) AS `ds2` +FROM (SELECT `key`, `value`, `ds1` +FROM `default`.`pcr_t1_n1` +WHERE ROW(`key`, `ds1`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) AND `ds2` = '2001-04-08' +ORDER BY `key`, `value`, `ds1`) AS `t1` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n1 + filterExpr: ((struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds2 = '2001-04-08')) (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n1] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 10 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, `t3`.`ds1` AS `ds11`, CAST('2001-04-08' AS STRING) AS `ds21` +FROM (SELECT * +FROM (SELECT `key`, `value`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value`, `ds1` +FROM `default`.`pcr_t1_n1` +WHERE `ds2` = '2001-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col3 (type: int), _col4 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), '2001-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds11`, `t3`.`ds20` AS `ds21` +FROM (SELECT * +FROM (SELECT `key`, `value`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value`, `ds2` +FROM `default`.`pcr_t1_n1` +WHERE `ds1` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string), _col2 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col3 (type: int), _col4 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2000-04-09' (type: string), VALUE._col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: (ds1) IN ('2000-04-08', '2000-04-09') (type: boolean) + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t1] + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [t1] + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 60 Data size: 27720 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key) IN (1, 2) (type: boolean) + Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-10 + ds2 2001-04-10 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n1 + name: default.pcr_t1_n1 + Truncated Path -> Alias: + /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [t2] + /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [t2] + /pcr_t1_n1/ds1=2000-04-10/ds2=2001-04-10 [t2] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Position of Big Table: 0 + residual filter predicates: {(struct(_col2,_col4)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2))} + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +2 val_2 2000-04-09 2001-04-09 +PREHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +PREHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +#### A masked pattern was here #### +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 +2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-08 2001-04-08 +4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 +8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-08 2001-04-08 +9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-08 2001-04-08 +10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-08 2001-04-08 +11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 +17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 +19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-08 2001-04-08 +PREHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 +2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-09 2001-04-09 +4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 +8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-09 2001-04-09 +9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-09 2001-04-09 +10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-09 2001-04-09 +11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 +17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 +19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-09 2001-04-09 +Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +POSTHOOK: query: select * +from pcr_t1_n1 t1 join pcr_t1_n1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 +#### A masked pattern was here #### +9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 +0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 +PREHOOK: query: drop table pcr_t1_n1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t1_n1 +PREHOOK: Output: default@pcr_t1_n1 +POSTHOOK: query: drop table pcr_t1_n1 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t1_n1 +POSTHOOK: Output: default@pcr_t1_n1 diff --git ql/src/test/results/clientpositive/llap/pointlookup4.q.out ql/src/test/results/clientpositive/llap/pointlookup4.q.out new file mode 100644 index 0000000000..3ca21d7460 --- /dev/null +++ ql/src/test/results/clientpositive/llap/pointlookup4.q.out @@ -0,0 +1,498 @@ +PREHOOK: query: drop table pcr_t1_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t1_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table pcr_t1_n0 (key int, value string) partitioned by (ds1 string, ds2 string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t1_n0 +POSTHOOK: query: create table pcr_t1_n0 (key int, value string) partitioned by (ds1 string, ds2 string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t1_n0 +PREHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-08,ds2=2001-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-08,ds2=2001-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-09,ds2=2001-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-09,ds2=2001-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1_n0@ds1=2000-04-10/ds2=2001-04-10 +POSTHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1_n0@ds1=2000-04-10/ds2=2001-04-10 +POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-10,ds2=2001-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-10,ds2=2001-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n0 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n0 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` +FROM `default`.`pcr_t1_n0` +WHERE `ds1` = '2000-04-08' AND `ds2` = '2001-04-08' AND `key` = 1 OR `ds1` = '2000-04-09' AND `ds2` = '2001-04-09' AND `key` = 2 +ORDER BY `key`, `value`, `ds1`, `ds2` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n0 + filterExpr: (((ds1 = '2000-04-08') and (ds2 = '2001-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (ds2 = '2001-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((ds1 = '2000-04-08') and (ds2 = '2001-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (ds2 = '2001-04-09') and (key = 2))) (type: boolean) + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n0 + name: default.pcr_t1_n0 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n0 + name: default.pcr_t1_n0 + Truncated Path -> Alias: + /pcr_t1_n0/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n0] + /pcr_t1_n0/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n0] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n0 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n0 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +2 val_2 2000-04-09 2001-04-09 +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n0 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n0 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` +FROM `default`.`pcr_t1_n0` +WHERE ROW(`key`, `ds1`, `ds2`) IN (ROW(1, '2000-04-08', '2001-04-08'), ROW(2, '2000-04-09', '2001-04-09')) +ORDER BY `key`, `value`, `ds1`, `ds2` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: pcr_t1_n0 + filterExpr: ((struct(key,ds1,ds2)) IN (const struct(1,'2000-04-08','2001-04-08'), const struct(2,'2000-04-09','2001-04-09')) and (struct(ds1,ds2)) IN (struct('2000-04-08','2001-04-08'), struct('2000-04-09','2001-04-09'))) (type: boolean) + Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(key,ds1,ds2)) IN (const struct(1,'2000-04-08','2001-04-08'), const struct(2,'2000-04-09','2001-04-09')) (type: boolean) + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + numBuckets: -1 + sort order: ++++ + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n0 + name: default.pcr_t1_n0 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1_n0 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1_n0 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1_n0 + name: default.pcr_t1_n0 + Truncated Path -> Alias: + /pcr_t1_n0/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n0] + /pcr_t1_n0/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n0] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pcr_t1_n0 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds1, ds2 +from pcr_t1_n0 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pcr_t1_n0 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 +#### A masked pattern was here #### +2 val_2 2000-04-09 2001-04-09 +PREHOOK: query: drop table pcr_t1_n0 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t1_n0 +PREHOOK: Output: default@pcr_t1_n0 +POSTHOOK: query: drop table pcr_t1_n0 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t1_n0 +POSTHOOK: Output: default@pcr_t1_n0 diff --git ql/src/test/results/clientpositive/llap/pointlookup5.q.out ql/src/test/results/clientpositive/llap/pointlookup5.q.out new file mode 100644 index 0000000000..d5d2a2affd --- /dev/null +++ ql/src/test/results/clientpositive/llap/pointlookup5.q.out @@ -0,0 +1,152 @@ +PREHOOK: query: create table t(a integer) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t +POSTHOOK: query: create table t(a integer) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t +PREHOOK: query: create table t2(b integer) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t2 +POSTHOOK: query: create table t2(b integer) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t2 +PREHOOK: query: insert into t values (1),(2),(3),(4) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t +POSTHOOK: query: insert into t values (1),(2),(3),(4) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t +POSTHOOK: Lineage: t.a SCRIPT [] +PREHOOK: query: insert into t2 values (1),(2),(3),(4) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t2 +POSTHOOK: query: insert into t2 values (1),(2),(3),(4) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t2 +POSTHOOK: Lineage: t2.b SCRIPT [] +PREHOOK: query: explain +select * from t,t2 where + a*a=b+3 + and + a in (1,2,3,4) + and + b in (1,2,3,4) + + and ( + (a in (1,2) and b in (1,2) ) or + (a in (2,3) and b in (2,3) ) + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@t +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from t,t2 where + a*a=b+3 + and + a in (1,2,3,4) + and + b in (1,2,3,4) + + and ( + (a in (1,2) and b in (1,2) ) or + (a in (2,3) and b in (2,3) ) + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t + filterExpr: (a) IN (1, 2, 3) (type: boolean) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (a) IN (1, 2, 3) (type: boolean) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: a (type: int), (a * a) (type: int), (a) IN (1, 2) (type: boolean), (a) IN (2, 3) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: boolean), _col3 (type: boolean) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (b) IN (1, 2, 3) (type: boolean) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (b) IN (1, 2, 3) (type: boolean) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: b (type: int), (b + 3) (type: int), (b) IN (1, 2) (type: boolean), (b) IN (2, 3) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: boolean), _col3 (type: boolean) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col2, _col3, _col4, _col6, _col7 + residual filter predicates: {((_col2 and _col6) or (_col3 and _col7))} + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col4 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/position_alias_test_1.q.out ql/src/test/results/clientpositive/llap/position_alias_test_1.q.out new file mode 100644 index 0000000000..043c18e212 --- /dev/null +++ ql/src/test/results/clientpositive/llap/position_alias_test_1.q.out @@ -0,0 +1,199 @@ +PREHOOK: query: create table alias_test_01(a INT, b STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@alias_test_01 +POSTHOOK: query: create table alias_test_01(a INT, b STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@alias_test_01 +PREHOOK: query: create table alias_test_02(a INT, b STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@alias_test_02 +POSTHOOK: query: create table alias_test_02(a INT, b STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@alias_test_02 +PREHOOK: query: create table alias_test_03(a INT, b STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@alias_test_03 +POSTHOOK: query: create table alias_test_03(a INT, b STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@alias_test_03 +Warning: Shuffle Join MERGEJOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain + select * from + alias_test_01 alias01 + left join + ( + select 2017 as a, b from alias_test_02 group by 1, 2 + ) alias02 + on alias01.a = alias02.a + left join + alias_test_03 alias03 + on alias01.a = alias03.a +PREHOOK: type: QUERY +PREHOOK: Input: default@alias_test_01 +PREHOOK: Input: default@alias_test_02 +PREHOOK: Input: default@alias_test_03 +#### A masked pattern was here #### +POSTHOOK: query: explain + select * from + alias_test_01 alias01 + left join + ( + select 2017 as a, b from alias_test_02 group by 1, 2 + ) alias02 + on alias01.a = alias02.a + left join + alias_test_03 alias03 + on alias01.a = alias03.a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alias_test_01 +POSTHOOK: Input: default@alias_test_02 +POSTHOOK: Input: default@alias_test_03 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alias01 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int), b (type: string), (a = 2017) (type: boolean) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: boolean) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: alias_test_02 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: b (type: string) + outputColumnNames: b + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: b (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: alias03 + filterExpr: a is not null (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: a is not null (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int), b (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + filter predicates: + 0 {VALUE._col2} + 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 1 Data size: 373 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 373 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 2017 (type: int), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/ppd1.q.out ql/src/test/results/clientpositive/llap/ppd1.q.out similarity index 63% rename from ql/src/test/results/clientpositive/ppd1.q.out rename to ql/src/test/results/clientpositive/llap/ppd1.q.out index 6137c04e7c..6acdf83c56 100644 --- ql/src/test/results/clientpositive/ppd1.q.out +++ ql/src/test/results/clientpositive/llap/ppd1.q.out @@ -9,38 +9,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Filter Operator + predicate: (key > '2') (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: SELECT src.key as c3 from src where src.key > '2' PREHOOK: type: QUERY @@ -442,38 +426,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Filter Operator + predicate: (key > '2') (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: SELECT src.key as c3 from src where src.key > '2' PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/ppd2.q.out ql/src/test/results/clientpositive/llap/ppd2.q.out new file mode 100644 index 0000000000..faa10a5771 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd2.q.out @@ -0,0 +1,693 @@ +PREHOOK: query: explain +select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: explain +select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 > 1L) (type: boolean) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +0 3 +100 2 +103 2 +104 2 +113 2 +118 2 +119 3 +12 2 +120 2 +125 2 +128 3 +129 2 +134 2 +137 2 +138 4 +146 2 +149 2 +15 2 +152 2 +164 2 +165 2 +167 3 +169 4 +172 2 +174 2 +175 2 +176 2 +179 2 +18 2 +187 3 +191 2 +193 3 +195 2 +197 2 +199 3 +200 2 +203 2 +205 2 +207 2 +208 3 +209 2 +213 2 +216 2 +217 2 +219 2 +221 2 +223 2 +224 2 +229 2 +230 5 +233 2 +237 2 +238 2 +239 2 +24 2 +242 2 +255 2 +256 2 +26 2 +265 2 +272 2 +273 3 +277 4 +278 2 +280 2 +281 2 +282 2 +288 2 +298 3 +307 2 +309 2 +311 3 +316 3 +317 2 +318 3 +321 2 +322 2 +325 2 +327 3 +331 2 +333 2 +342 2 +344 2 +348 5 +35 3 +353 2 +367 2 +369 3 +37 2 +382 2 +384 3 +395 2 +396 3 +397 2 +399 2 +401 5 +403 3 +404 2 +406 4 +409 3 +413 2 +414 2 +417 3 +42 2 +424 2 +429 2 +430 3 +431 3 +438 3 +439 2 +454 3 +458 2 +459 2 +462 2 +463 2 +466 3 +468 4 +469 5 +478 2 +480 3 +489 4 +492 2 +498 3 +5 3 +51 2 +58 2 +67 2 +70 3 +72 2 +76 2 +83 2 +84 2 +90 3 +95 2 +97 2 +98 2 +PREHOOK: query: EXPLAIN +SELECT user_id +FROM ( + SELECT + CAST(key AS INT) AS user_id + ,CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%') + THEN 1 + ELSE 0 END AS tag_student + FROM srcpart +) sub +WHERE sub.tag_student > 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT user_id +FROM ( + SELECT + CAST(key AS INT) AS user_id + ,CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%') + THEN 1 + ELSE 0 END AS tag_student + FROM srcpart +) sub +WHERE sub.tag_student > 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + filterExpr: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) + Filter Operator + predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) + Select Operator + expressions: UDFToInteger(key) (type: int) + outputColumnNames: _col0 + ListSink + +PREHOOK: query: EXPLAIN +SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (key = 20) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 20) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: y + filterExpr: (key = 20) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 20) (type: boolean) + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: explain +select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Filter Operator + predicate: (_col1 > 1L) (type: boolean) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +POSTHOOK: query: select b.key,b.cc +from ( + select a.* + from ( + select key, count(value) as cc + from srcpart a + where a.ds = '2008-04-08' and a.hr = '11' + group by key + )a + distribute by a.key + sort by a.key,a.cc desc) b +where b.cc>1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +#### A masked pattern was here #### +0 3 +100 2 +103 2 +104 2 +113 2 +118 2 +119 3 +12 2 +120 2 +125 2 +128 3 +129 2 +134 2 +137 2 +138 4 +146 2 +149 2 +15 2 +152 2 +164 2 +165 2 +167 3 +169 4 +172 2 +174 2 +175 2 +176 2 +179 2 +18 2 +187 3 +191 2 +193 3 +195 2 +197 2 +199 3 +200 2 +203 2 +205 2 +207 2 +208 3 +209 2 +213 2 +216 2 +217 2 +219 2 +221 2 +223 2 +224 2 +229 2 +230 5 +233 2 +237 2 +238 2 +239 2 +24 2 +242 2 +255 2 +256 2 +26 2 +265 2 +272 2 +273 3 +277 4 +278 2 +280 2 +281 2 +282 2 +288 2 +298 3 +307 2 +309 2 +311 3 +316 3 +317 2 +318 3 +321 2 +322 2 +325 2 +327 3 +331 2 +333 2 +342 2 +344 2 +348 5 +35 3 +353 2 +367 2 +369 3 +37 2 +382 2 +384 3 +395 2 +396 3 +397 2 +399 2 +401 5 +403 3 +404 2 +406 4 +409 3 +413 2 +414 2 +417 3 +42 2 +424 2 +429 2 +430 3 +431 3 +438 3 +439 2 +454 3 +458 2 +459 2 +462 2 +463 2 +466 3 +468 4 +469 5 +478 2 +480 3 +489 4 +492 2 +498 3 +5 3 +51 2 +58 2 +67 2 +70 3 +72 2 +76 2 +83 2 +84 2 +90 3 +95 2 +97 2 +98 2 diff --git ql/src/test/results/clientpositive/llap/ppd_clusterby.q.out ql/src/test/results/clientpositive/llap/ppd_clusterby.q.out new file mode 100644 index 0000000000..f1d60992eb --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_clusterby.q.out @@ -0,0 +1,371 @@ +PREHOOK: query: EXPLAIN +SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (key = 10) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 10) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +10 val_10 +PREHOOK: query: EXPLAIN +SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (key = 20) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 20) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: y + filterExpr: (key = 20) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 20) (type: boolean) + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +20 val_20 20 +PREHOOK: query: EXPLAIN +SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (key = 10) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 10) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +10 val_10 +PREHOOK: query: EXPLAIN +SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + filterExpr: (key = 20) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 20) (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: y + filterExpr: (key = 20) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 20) (type: boolean) + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +20 val_20 20 diff --git ql/src/test/results/clientpositive/llap/ppd_constant_expr.q.out ql/src/test/results/clientpositive/llap/ppd_constant_expr.q.out new file mode 100644 index 0000000000..d527113b73 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_constant_expr.q.out @@ -0,0 +1,294 @@ +PREHOOK: query: CREATE TABLE ppd_constant_expr(c1 STRING, c2 INT, c3 DOUBLE) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ppd_constant_expr +POSTHOOK: query: CREATE TABLE ppd_constant_expr(c1 STRING, c2 INT, c3 DOUBLE) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ppd_constant_expr +PREHOOK: query: EXPLAIN +FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +PREHOOK: Output: default@ppd_constant_expr +POSTHOOK: query: EXPLAIN +FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +POSTHOOK: Output: default@ppd_constant_expr +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: null (type: string), null (type: int), null (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ppd_constant_expr + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) + outputColumnNames: c1, c2, c3 + Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll') + minReductionHashAggr: 0.96 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ppd_constant_expr + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3 + Column Types: string, int, double + Table: default.ppd_constant_expr + +PREHOOK: query: FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +PREHOOK: Output: default@ppd_constant_expr +POSTHOOK: query: FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +POSTHOOK: Output: default@ppd_constant_expr +POSTHOOK: Lineage: ppd_constant_expr.c1 EXPRESSION [] +POSTHOOK: Lineage: ppd_constant_expr.c2 EXPRESSION [] +POSTHOOK: Lineage: ppd_constant_expr.c3 EXPRESSION [] +PREHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr +PREHOOK: type: QUERY +PREHOOK: Input: default@ppd_constant_expr +#### A masked pattern was here #### +POSTHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ppd_constant_expr +#### A masked pattern was here #### +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +PREHOOK: query: EXPLAIN +FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +PREHOOK: Output: default@ppd_constant_expr +POSTHOOK: query: EXPLAIN +FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +POSTHOOK: Output: default@ppd_constant_expr +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: null (type: string), null (type: int), null (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ppd_constant_expr + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) + outputColumnNames: c1, c2, c3 + Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll') + minReductionHashAggr: 0.96 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.ppd_constant_expr + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3 + Column Types: string, int, double + Table: default.ppd_constant_expr + +PREHOOK: query: FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +PREHOOK: Output: default@ppd_constant_expr +POSTHOOK: query: FROM src1 +INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +POSTHOOK: Output: default@ppd_constant_expr +POSTHOOK: Lineage: ppd_constant_expr.c1 EXPRESSION [] +POSTHOOK: Lineage: ppd_constant_expr.c2 EXPRESSION [] +POSTHOOK: Lineage: ppd_constant_expr.c3 EXPRESSION [] +PREHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr +PREHOOK: type: QUERY +PREHOOK: Input: default@ppd_constant_expr +#### A masked pattern was here #### +POSTHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ppd_constant_expr +#### A masked pattern was here #### +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL +NULL NULL NULL diff --git ql/src/test/results/clientpositive/ppd_deterministic_expr.q.out ql/src/test/results/clientpositive/llap/ppd_deterministic_expr.q.out similarity index 67% rename from ql/src/test/results/clientpositive/ppd_deterministic_expr.q.out rename to ql/src/test/results/clientpositive/llap/ppd_deterministic_expr.q.out index 28f5e1f53b..662a793afe 100644 --- ql/src/test/results/clientpositive/ppd_deterministic_expr.q.out +++ ql/src/test/results/clientpositive/llap/ppd_deterministic_expr.q.out @@ -353,58 +353,70 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: testa - filterExpr: (part1) IN ('US', 'CA') (type: boolean) - Statistics: Num rows: 2 Data size: 532 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: CAST( col1 AS decimal(38,18)) (type: decimal(38,18)), CAST( col2 AS decimal(38,18)) (type: decimal(38,18)), CAST( col3 AS decimal(38,18)) (type: decimal(38,18)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 'US' (type: char(2)), 'DEF' (type: char(3)), '200' (type: char(3)) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: 'US' (type: char(2)), 'DEF' (type: char(3)), '200' (type: char(3)) - Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)) - TableScan - alias: testb - filterExpr: (part1) IN ('US', 'CA') (type: boolean) - Statistics: Num rows: 2 Data size: 1084 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: CAST( cola AS decimal(38,18)) (type: decimal(38,18)), CAST( colb AS decimal(38,18)) (type: decimal(38,18)), CAST( part1 AS CHAR(2)) (type: char(2)), CAST( part2 AS CHAR(3)) (type: char(3)) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 2 Data size: 1156 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col3 (type: char(2)), _col4 (type: char(3)), '200' (type: char(3)) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col3 (type: char(2)), _col4 (type: char(3)), '200' (type: char(3)) - Statistics: Num rows: 2 Data size: 1156 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col5 (type: char(2)), _col6 (type: char(3)), _col7 (type: char(3)) - 1 _col3 (type: char(2)), _col4 (type: char(3)), _col5 (type: char(3)) - outputColumnNames: _col0, _col1, _col2, _col8, _col9 - Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), _col8 (type: decimal(38,18)), _col9 (type: decimal(38,18)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: testa + Statistics: Num rows: 2 Data size: 532 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( col1 AS decimal(38,18)) (type: decimal(38,18)), CAST( col2 AS decimal(38,18)) (type: decimal(38,18)), CAST( col3 AS decimal(38,18)) (type: decimal(38,18)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 'US' (type: char(2)), 'DEF' (type: char(3)), '200' (type: char(3)) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: 'US' (type: char(2)), 'DEF' (type: char(3)), '200' (type: char(3)) + Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: testb + Statistics: Num rows: 2 Data size: 1084 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( cola AS decimal(38,18)) (type: decimal(38,18)), CAST( colb AS decimal(38,18)) (type: decimal(38,18)), CAST( part1 AS CHAR(2)) (type: char(2)), CAST( part2 AS CHAR(3)) (type: char(3)) + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 2 Data size: 1156 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: char(2)), _col4 (type: char(3)), '200' (type: char(3)) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col3 (type: char(2)), _col4 (type: char(3)), '200' (type: char(3)) + Statistics: Num rows: 2 Data size: 1156 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 'US' (type: char(2)), 'DEF' (type: char(3)), '200' (type: char(3)) + 1 _col3 (type: char(2)), _col4 (type: char(3)), '200' (type: char(3)) + outputColumnNames: _col0, _col1, _col2, _col8, _col9 + Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), _col8 (type: decimal(38,18)), _col9 (type: decimal(38,18)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -444,10 +456,10 @@ POSTHOOK: Input: default@testb@part1=US/part2=DEF/part3=200 POSTHOOK: Input: default@viewdeterministicudfa POSTHOOK: Input: default@viewdeterministicudfb #### A masked pattern was here #### -12.341000000000000000 1001.000000000000000000 2001.000000000000000000 601.000000000000000000 701.000000000000000000 -12.341000000000000000 1001.000000000000000000 2001.000000000000000000 600.000000000000000000 700.000000000000000000 -12.340000000000000000 100.000000000000000000 200.000000000000000000 601.000000000000000000 701.000000000000000000 12.340000000000000000 100.000000000000000000 200.000000000000000000 600.000000000000000000 700.000000000000000000 +12.340000000000000000 100.000000000000000000 200.000000000000000000 601.000000000000000000 701.000000000000000000 +12.341000000000000000 1001.000000000000000000 2001.000000000000000000 600.000000000000000000 700.000000000000000000 +12.341000000000000000 1001.000000000000000000 2001.000000000000000000 601.000000000000000000 701.000000000000000000 PREHOOK: query: explain select vcol1, vcol2, vcol3, vcola, vcolb from viewNoUDFA a inner join viewNoUDFB b @@ -488,58 +500,102 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: testa - filterExpr: ((part1) IN ('US', 'CA') and (part1 = 'US') and (part2 = 'DEF') and (part3 = '200')) (type: boolean) - Statistics: Num rows: 2 Data size: 532 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: CAST( col1 AS decimal(38,18)) (type: decimal(38,18)), CAST( col2 AS decimal(38,18)) (type: decimal(38,18)), CAST( col3 AS decimal(38,18)) (type: decimal(38,18)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 'US' (type: string), 'DEF' (type: string), '200' (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: 'US' (type: string), 'DEF' (type: string), '200' (type: string) - Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)) - TableScan - alias: testb - filterExpr: ((part1) IN ('US', 'CA') and (part3 = '200') and part1 is not null and part2 is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 1084 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: CAST( cola AS decimal(38,18)) (type: decimal(38,18)), CAST( colb AS decimal(38,18)) (type: decimal(38,18)), part1 (type: string), part2 (type: string) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 2 Data size: 1546 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col3 (type: string), _col4 (type: string), '200' (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col3 (type: string), _col4 (type: string), '200' (type: string) - Statistics: Num rows: 2 Data size: 1546 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col5 (type: string), _col6 (type: string), _col7 (type: string) - 1 _col3 (type: string), _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2, _col8, _col9 - Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), _col8 (type: decimal(38,18)), _col9 (type: decimal(38,18)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: testa + Statistics: Num rows: 2 Data size: 532 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( col1 AS decimal(38,18)) (type: decimal(38,18)), CAST( col2 AS decimal(38,18)) (type: decimal(38,18)), CAST( col3 AS decimal(38,18)) (type: decimal(38,18)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 'US' (type: string), 'DEF' (type: string), '200' (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: 'US' (type: string), 'DEF' (type: string), '200' (type: string) + Statistics: Num rows: 2 Data size: 1604 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)) + Select Operator + expressions: 'US' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE + Dynamic Partitioning Event Operator + Target column: part1 (string) + Target Input: testb + Partition key expr: part1 + Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE + Target Vertex: Map 3 + Select Operator + expressions: 'DEF' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Dynamic Partitioning Event Operator + Target column: part2 (string) + Target Input: testb + Partition key expr: part2 + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Target Vertex: Map 3 + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: testb + Statistics: Num rows: 2 Data size: 1084 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( cola AS decimal(38,18)) (type: decimal(38,18)), CAST( colb AS decimal(38,18)) (type: decimal(38,18)), part1 (type: string), part2 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 2 Data size: 1546 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col3 (type: string), _col4 (type: string), '200' (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col3 (type: string), _col4 (type: string), '200' (type: string) + Statistics: Num rows: 2 Data size: 1546 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 'US' (type: string), 'DEF' (type: string), '200' (type: string) + 1 _col3 (type: string), _col4 (type: string), '200' (type: string) + outputColumnNames: _col0, _col1, _col2, _col8, _col9 + Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), _col8 (type: decimal(38,18)), _col9 (type: decimal(38,18)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 2240 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -579,7 +635,7 @@ POSTHOOK: Input: default@testb@part1=US/part2=DEF/part3=200 POSTHOOK: Input: default@viewnoudfa POSTHOOK: Input: default@viewnoudfb #### A masked pattern was here #### -12.341000000000000000 1001.000000000000000000 2001.000000000000000000 601.000000000000000000 701.000000000000000000 -12.341000000000000000 1001.000000000000000000 2001.000000000000000000 600.000000000000000000 700.000000000000000000 -12.340000000000000000 100.000000000000000000 200.000000000000000000 601.000000000000000000 701.000000000000000000 12.340000000000000000 100.000000000000000000 200.000000000000000000 600.000000000000000000 700.000000000000000000 +12.340000000000000000 100.000000000000000000 200.000000000000000000 601.000000000000000000 701.000000000000000000 +12.341000000000000000 1001.000000000000000000 2001.000000000000000000 600.000000000000000000 700.000000000000000000 +12.341000000000000000 1001.000000000000000000 2001.000000000000000000 601.000000000000000000 701.000000000000000000 diff --git ql/src/test/results/clientpositive/ppd_gby.q.out ql/src/test/results/clientpositive/llap/ppd_gby.q.out similarity index 50% rename from ql/src/test/results/clientpositive/ppd_gby.q.out rename to ql/src/test/results/clientpositive/llap/ppd_gby.q.out index 05fcaab669..af5537f19d 100644 --- ql/src/test/results/clientpositive/ppd_gby.q.out +++ ql/src/test/results/clientpositive/llap/ppd_gby.q.out @@ -20,51 +20,60 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (value > 'val_200') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (value > 'val_200') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(key) + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count(key) - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) - Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -89,59 +98,91 @@ POSTHOOK: Input: default@src val_201 val_202 val_203 -val_205 val_207 val_208 val_209 +val_216 +val_222 +val_223 +val_228 +val_229 +val_230 +val_233 +val_239 +val_244 +val_247 +val_248 +val_256 +val_26 +val_27 +val_273 +val_274 +val_282 +val_283 +val_296 +val_298 +val_302 +val_306 +val_308 +val_309 +val_310 +val_311 +val_321 +val_325 +val_33 +val_331 +val_332 +val_336 +val_338 +val_341 +val_342 +val_35 +val_351 +val_353 +val_360 +val_364 +val_368 +val_369 +val_373 +val_374 +val_377 +val_378 +val_384 +val_386 +val_389 +val_397 +val_205 val_213 val_214 -val_216 val_217 val_218 val_219 val_221 -val_222 -val_223 val_224 val_226 -val_228 -val_229 -val_230 -val_233 val_235 val_237 val_238 -val_239 val_24 val_241 val_242 -val_244 -val_247 -val_248 val_249 val_252 val_255 -val_256 val_257 val_258 -val_26 val_260 val_262 val_263 val_265 val_266 -val_27 val_272 -val_273 -val_274 val_275 val_277 val_278 val_28 val_280 val_281 -val_282 -val_283 val_284 val_285 val_286 @@ -150,69 +191,37 @@ val_288 val_289 val_291 val_292 -val_296 -val_298 val_30 -val_302 val_305 -val_306 val_307 -val_308 -val_309 -val_310 -val_311 val_315 val_316 val_317 val_318 -val_321 val_322 val_323 -val_325 val_327 -val_33 -val_331 -val_332 val_333 val_335 -val_336 -val_338 val_339 val_34 -val_341 -val_342 val_344 val_345 val_348 -val_35 -val_351 -val_353 val_356 -val_360 val_362 -val_364 val_365 val_366 val_367 -val_368 -val_369 val_37 -val_373 -val_374 val_375 -val_377 -val_378 val_379 val_382 -val_384 -val_386 -val_389 val_392 val_393 val_394 val_395 val_396 -val_397 val_399 val_4 PREHOOK: query: EXPLAIN @@ -237,51 +246,60 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (value > 'val_200') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (value > 'val_200') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(key) + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count(key) - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) - Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 54 Data size: 4914 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -306,59 +324,91 @@ POSTHOOK: Input: default@src val_201 val_202 val_203 -val_205 val_207 val_208 val_209 +val_216 +val_222 +val_223 +val_228 +val_229 +val_230 +val_233 +val_239 +val_244 +val_247 +val_248 +val_256 +val_26 +val_27 +val_273 +val_274 +val_282 +val_283 +val_296 +val_298 +val_302 +val_306 +val_308 +val_309 +val_310 +val_311 +val_321 +val_325 +val_33 +val_331 +val_332 +val_336 +val_338 +val_341 +val_342 +val_35 +val_351 +val_353 +val_360 +val_364 +val_368 +val_369 +val_373 +val_374 +val_377 +val_378 +val_384 +val_386 +val_389 +val_397 +val_205 val_213 val_214 -val_216 val_217 val_218 val_219 val_221 -val_222 -val_223 val_224 val_226 -val_228 -val_229 -val_230 -val_233 val_235 val_237 val_238 -val_239 val_24 val_241 val_242 -val_244 -val_247 -val_248 val_249 val_252 val_255 -val_256 val_257 val_258 -val_26 val_260 val_262 val_263 val_265 val_266 -val_27 val_272 -val_273 -val_274 val_275 val_277 val_278 val_28 val_280 val_281 -val_282 -val_283 val_284 val_285 val_286 @@ -367,68 +417,36 @@ val_288 val_289 val_291 val_292 -val_296 -val_298 val_30 -val_302 val_305 -val_306 val_307 -val_308 -val_309 -val_310 -val_311 val_315 val_316 val_317 val_318 -val_321 val_322 val_323 -val_325 val_327 -val_33 -val_331 -val_332 val_333 val_335 -val_336 -val_338 val_339 val_34 -val_341 -val_342 val_344 val_345 val_348 -val_35 -val_351 -val_353 val_356 -val_360 val_362 -val_364 val_365 val_366 val_367 -val_368 -val_369 val_37 -val_373 -val_374 val_375 -val_377 -val_378 val_379 val_382 -val_384 -val_386 -val_389 val_392 val_393 val_394 val_395 val_396 -val_397 val_399 val_4 diff --git ql/src/test/results/clientpositive/llap/ppd_gby2.q.out ql/src/test/results/clientpositive/llap/ppd_gby2.q.out new file mode 100644 index 0000000000..007b434258 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_gby2.q.out @@ -0,0 +1,260 @@ +PREHOOK: query: EXPLAIN +SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (value > 'val_200') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (value > 'val_200') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(key) + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(_col0) + keys: _col1 (type: bigint) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: bigint) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: bigint) + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + keys: KEY._col0 (type: bigint) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +val_399 2 +val_396 3 +val_348 5 +val_4 1 +val_277 4 +PREHOOK: query: EXPLAIN +SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (value > 'val_200') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (value > 'val_200') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(key) + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) + Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(_col0) + keys: _col1 (type: bigint) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: bigint) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: bigint) + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + keys: KEY._col0 (type: bigint) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT max(src1.c1), src1.c2 +FROM +(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 +WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') +GROUP BY src1.c2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +val_399 2 +val_396 3 +val_348 5 +val_4 1 +val_277 4 diff --git ql/src/test/results/clientpositive/llap/ppd_gby_join.q.out ql/src/test/results/clientpositive/llap/ppd_gby_join.q.out new file mode 100644 index 0000000000..b9081e10bc --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_gby_join.q.out @@ -0,0 +1,556 @@ +PREHOOK: query: EXPLAIN +SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 56 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col0 (type: string) + minReductionHashAggr: 0.58928573 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +200 4 +201 1 +202 1 +203 4 +205 4 +207 4 +208 9 +209 4 +213 4 +214 1 +216 4 +217 4 +218 1 +219 4 +221 4 +222 1 +223 4 +224 4 +226 1 +228 1 +229 4 +230 25 +233 4 +235 1 +237 4 +238 4 +239 4 +24 4 +241 1 +242 4 +244 1 +247 1 +248 1 +249 1 +252 1 +255 4 +256 4 +257 1 +258 1 +26 4 +260 1 +262 1 +263 1 +265 4 +266 1 +27 1 +272 4 +273 9 +274 1 +275 1 +277 16 +278 4 +28 1 +280 4 +281 4 +282 4 +283 1 +284 1 +285 1 +286 1 +287 1 +288 4 +289 1 +291 1 +292 1 +296 1 +298 9 +30 1 +302 1 +305 1 +306 1 +307 4 +308 1 +309 4 +310 1 +311 9 +315 1 +316 9 +317 4 +318 9 +321 4 +322 4 +323 1 +325 4 +327 9 +33 1 +331 4 +332 1 +333 4 +335 1 +336 1 +338 1 +339 1 +34 1 +341 1 +342 4 +344 4 +345 1 +348 25 +35 9 +351 1 +353 4 +356 1 +360 1 +362 1 +364 1 +365 1 +366 1 +367 4 +368 1 +369 9 +37 4 +373 1 +374 1 +375 1 +377 1 +378 1 +379 1 +382 4 +384 9 +386 1 +389 1 +392 1 +393 1 +394 1 +395 4 +396 9 +397 4 +399 4 +PREHOOK: query: EXPLAIN +SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 56 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: _col0 (type: string) + minReductionHashAggr: 0.58928573 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.c1, count(1) +FROM +(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 +JOIN +(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 AND src1.c1 < '400' +WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') +GROUP BY src1.c1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +200 4 +201 1 +202 1 +203 4 +205 4 +207 4 +208 9 +209 4 +213 4 +214 1 +216 4 +217 4 +218 1 +219 4 +221 4 +222 1 +223 4 +224 4 +226 1 +228 1 +229 4 +230 25 +233 4 +235 1 +237 4 +238 4 +239 4 +24 4 +241 1 +242 4 +244 1 +247 1 +248 1 +249 1 +252 1 +255 4 +256 4 +257 1 +258 1 +26 4 +260 1 +262 1 +263 1 +265 4 +266 1 +27 1 +272 4 +273 9 +274 1 +275 1 +277 16 +278 4 +28 1 +280 4 +281 4 +282 4 +283 1 +284 1 +285 1 +286 1 +287 1 +288 4 +289 1 +291 1 +292 1 +296 1 +298 9 +30 1 +302 1 +305 1 +306 1 +307 4 +308 1 +309 4 +310 1 +311 9 +315 1 +316 9 +317 4 +318 9 +321 4 +322 4 +323 1 +325 4 +327 9 +33 1 +331 4 +332 1 +333 4 +335 1 +336 1 +338 1 +339 1 +34 1 +341 1 +342 4 +344 4 +345 1 +348 25 +35 9 +351 1 +353 4 +356 1 +360 1 +362 1 +364 1 +365 1 +366 1 +367 4 +368 1 +369 9 +37 4 +373 1 +374 1 +375 1 +377 1 +378 1 +379 1 +382 4 +384 9 +386 1 +389 1 +392 1 +393 1 +394 1 +395 4 +396 9 +397 4 +399 4 diff --git ql/src/test/results/clientpositive/ppd_join.q.out ql/src/test/results/clientpositive/llap/ppd_join.q.out similarity index 64% rename from ql/src/test/results/clientpositive/ppd_join.q.out rename to ql/src/test/results/clientpositive/llap/ppd_join.q.out index 1117d34abc..86f9b5ec57 100644 --- ql/src/test/results/clientpositive/ppd_join.q.out +++ ql/src/test/results/clientpositive/llap/ppd_join.q.out @@ -26,63 +26,77 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -556,63 +570,77 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) + Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 56 Data size: 9968 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/ppd_join2.q.out ql/src/test/results/clientpositive/llap/ppd_join2.q.out similarity index 77% rename from ql/src/test/results/clientpositive/ppd_join2.q.out rename to ql/src/test/results/clientpositive/llap/ppd_join2.q.out index c09fefe225..28289eac59 100644 --- ql/src/test/results/clientpositive/ppd_join2.q.out +++ ql/src/test/results/clientpositive/llap/ppd_join2.q.out @@ -28,116 +28,115 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311')) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: src - filterExpr: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col2 (type: string) - TableScan - alias: src - filterExpr: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) or ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311'))) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311')) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + residual filter predicates: {((_col0 <> '10') or (_col2 <> '10'))} + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col3 (type: string) null sort order: z sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1719,116 +1718,115 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311')) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: src - filterExpr: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean) - Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col2 (type: string) - TableScan - alias: src - filterExpr: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '400') and (key <> '14') and (key <> '302') and (key <> '305') and (key <> '311') and ((value <> 'val_50') or (key > '1')) and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) or ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311'))) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key <> '306') and (sqrt(key) <> 13.0D) and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '400') and (key <> '14') and (key <> '305') and (key <> '302') and (key <> '311')) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + residual filter predicates: {((_col0 <> '10') or (_col2 <> '10'))} + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col3 (type: string) null sort order: z sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 262 Data size: 93272 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 426 Data size: 75828 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/ppd_join3.q.out ql/src/test/results/clientpositive/llap/ppd_join3.q.out similarity index 77% rename from ql/src/test/results/clientpositive/ppd_join3.q.out rename to ql/src/test/results/clientpositive/llap/ppd_join3.q.out index 71bf59fbc1..8f09bfc0d5 100644 --- ql/src/test/results/clientpositive/ppd_join3.q.out +++ ql/src/test/results/clientpositive/llap/ppd_join3.q.out @@ -28,114 +28,113 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1'))) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1'))) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) or ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1')))) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Filter Operator + predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1'))) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) null sort order: z sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2, _col3 + residual filter predicates: {((_col2 > '10') or (_col1 <> '10'))} + Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1774,114 +1773,113 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1'))) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1'))) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '0') and (key < '400') and (key <> '1') and (key <> '4') and (key <> '13') and (key <> '11') and (key <> '12')) (type: boolean) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) or ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1')))) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '12') and (key <> '11') and (key <> '13')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Filter Operator + predicate: ((key > '0') and (key < '400') and (key <> '4') and (key <> '1') and (key <> '11') and (key <> '12') and (key <> '13') and ((value <> 'val_500') or (key > '1'))) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) null sort order: z sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col2 > '10') or (_col1 <> '10')) (type: boolean) - Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 86 Data size: 7482 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2, _col3 + residual filter predicates: {((_col2 > '10') or (_col1 <> '10'))} + Statistics: Num rows: 135 Data size: 35775 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/ppd_join4.q.out ql/src/test/results/clientpositive/llap/ppd_join4.q.out new file mode 100644 index 0000000000..b8f896f6df --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_join4.q.out @@ -0,0 +1,142 @@ +PREHOOK: query: create table dual(a string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dual +POSTHOOK: query: create table dual(a string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dual +PREHOOK: query: drop table if exists test_tbl +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists test_tbl +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table test_tbl (id string,name string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test_tbl +POSTHOOK: query: create table test_tbl (id string,name string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_tbl +PREHOOK: query: insert into table test_tbl +select 'a','b' from dual +PREHOOK: type: QUERY +PREHOOK: Input: default@dual +PREHOOK: Output: default@test_tbl +POSTHOOK: query: insert into table test_tbl +select 'a','b' from dual +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dual +POSTHOOK: Output: default@test_tbl +POSTHOOK: Lineage: test_tbl.id SIMPLE [] +POSTHOOK: Lineage: test_tbl.name SIMPLE [] +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain +select t2.* +from +(select id,name from (select id,name from test_tbl) t1 sort by id) t2 +join test_tbl t3 on (t2.id=t3.id ) +where t2.name='c' and t3.id='a' +PREHOOK: type: QUERY +PREHOOK: Input: default@test_tbl +#### A masked pattern was here #### +POSTHOOK: query: explain +select t2.* +from +(select id,name from (select id,name from test_tbl) t1 sort by id) t2 +join test_tbl t3 on (t2.id=t3.id ) +where t2.name='c' and t3.id='a' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_tbl +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 3 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test_tbl + filterExpr: ((name = 'c') and (id = 'a')) (type: boolean) + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((name = 'c') and (id = 'a')) (type: boolean) + Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: t3 + filterExpr: (id = 'a') (type: boolean) + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (id = 'a') (type: boolean) + Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'a' (type: string), 'c' (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select t2.* +from +(select id,name from (select id,name from test_tbl) t1 sort by id) t2 +join test_tbl t3 on (t2.id=t3.id ) +where t2.name='c' and t3.id='a' +PREHOOK: type: QUERY +PREHOOK: Input: default@test_tbl +#### A masked pattern was here #### +POSTHOOK: query: select t2.* +from +(select id,name from (select id,name from test_tbl) t1 sort by id) t2 +join test_tbl t3 on (t2.id=t3.id ) +where t2.name='c' and t3.id='a' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_tbl +#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/llap/ppd_join5.q.out ql/src/test/results/clientpositive/llap/ppd_join5.q.out new file mode 100644 index 0000000000..f6346fd05c --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_join5.q.out @@ -0,0 +1,337 @@ +PREHOOK: query: create table t1_n79 (id1 string, id2 string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t1_n79 +POSTHOOK: query: create table t1_n79 (id1 string, id2 string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1_n79 +PREHOOK: query: create table t2_n48 (id string, d int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t2_n48 +POSTHOOK: query: create table t2_n48 (id string, d int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t2_n48 +PREHOOK: query: from src tablesample (1 rows) + insert into table t1_n79 select 'a','a' + insert into table t2_n48 select 'a',2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@t1_n79 +PREHOOK: Output: default@t2_n48 +POSTHOOK: query: from src tablesample (1 rows) + insert into table t1_n79 select 'a','a' + insert into table t2_n48 select 'a',2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@t1_n79 +POSTHOOK: Output: default@t2_n48 +POSTHOOK: Lineage: t1_n79.id1 SIMPLE [] +POSTHOOK: Lineage: t1_n79.id2 SIMPLE [] +POSTHOOK: Lineage: t2_n48.d SIMPLE [] +POSTHOOK: Lineage: t2_n48.id SIMPLE [] +Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain +select a.*,b.d d1,c.d d2 from + t1_n79 a join t2_n48 b on (a.id1 = b.id) + join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n79 +PREHOOK: Input: default@t2_n48 +#### A masked pattern was here #### +POSTHOOK: query: explain +select a.*,b.d d1,c.d d2 from + t1_n79 a join t2_n48 b on (a.id1 = b.id) + join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n79 +POSTHOOK: Input: default@t2_n48 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (id1 is not null and id2 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (id1 is not null and id2 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id1 (type: string), id2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: c + filterExpr: (d <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((d <= 1) and id is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d <= 1) and id is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id (type: string), d (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col0 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4 + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[41][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain +select * from ( +select a.*,b.d d1,c.d d2 from + t1_n79 a join t2_n48 b on (a.id1 = b.id) + join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 +) z where d1 > 1 or d2 > 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n79 +PREHOOK: Input: default@t2_n48 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from ( +select a.*,b.d d1,c.d d2 from + t1_n79 a join t2_n48 b on (a.id1 = b.id) + join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 +) z where d1 > 1 or d2 > 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n79 +POSTHOOK: Input: default@t2_n48 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (XPROD_EDGE), Reducer 2 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (id1 is not null and id2 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (id1 is not null and id2 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id1 (type: string), id2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((d <= 1) and id is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((d <= 1) and id is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: id (type: string), d (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col0 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col0 (type: string) + Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: c + filterExpr: (d <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (d <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: d (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 0 + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[41][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: select * from ( +select a.*,b.d d1,c.d d2 from + t1_n79 a join t2_n48 b on (a.id1 = b.id) + join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 +) z where d1 > 1 or d2 > 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n79 +PREHOOK: Input: default@t2_n48 +#### A masked pattern was here #### +POSTHOOK: query: select * from ( +select a.*,b.d d1,c.d d2 from + t1_n79 a join t2_n48 b on (a.id1 = b.id) + join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 +) z where d1 > 1 or d2 > 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n79 +POSTHOOK: Input: default@t2_n48 +#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/llap/ppd_join_filter.q.out ql/src/test/results/clientpositive/llap/ppd_join_filter.q.out new file mode 100644 index 0000000000..5145494c27 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_join_filter.q.out @@ -0,0 +1,1043 @@ +PREHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` +FROM (SELECT `key` +FROM `default`.`src` +WHERE `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` +FROM `default`.`src` +WHERE `key` IS NOT NULL +GROUP BY `key` +HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Group By Operator + aggregations: min(key) + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types string:double:double + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: double), _col2 (type: double) + auto parallelism: true + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 2.0 3.0 +0 2.0 3.0 +0 2.0 3.0 +2 4.0 5.0 +PREHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` +FROM (SELECT `key` +FROM `default`.`src` +WHERE `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` +FROM `default`.`src` +WHERE `key` IS NOT NULL +GROUP BY `key` +HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Group By Operator + aggregations: min(key) + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types string:double:double + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: double), _col2 (type: double) + auto parallelism: true + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 2.0 3.0 +0 2.0 3.0 +0 2.0 3.0 +2 4.0 5.0 +PREHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` +FROM (SELECT `key` +FROM `default`.`src` +WHERE `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` +FROM `default`.`src` +WHERE `key` IS NOT NULL +GROUP BY `key` +HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Group By Operator + aggregations: min(key) + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types string:double:double + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: double), _col2 (type: double) + auto parallelism: true + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 2.0 3.0 +0 2.0 3.0 +0 2.0 3.0 +2 4.0 5.0 +PREHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain extended select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` +FROM (SELECT `key` +FROM `default`.`src` +WHERE `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` +FROM `default`.`src` +WHERE `key` IS NOT NULL +GROUP BY `key` +HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Group By Operator + aggregations: min(key) + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types string:double:double + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) + Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: double), _col2 (type: double) + auto parallelism: true + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select a.key, b.k2, b.k3 +from src a +join ( +select key, +min(key) as k, +min(key)+1 as k1, +min(key)+2 as k2, +min(key)+3 as k3 +from src +group by key +) b +on a.key=b.key and b.k1 < 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 2.0 3.0 +0 2.0 3.0 +0 2.0 3.0 +2 4.0 5.0 diff --git ql/src/test/results/clientpositive/ppd_multi_insert.q.out ql/src/test/results/clientpositive/llap/ppd_multi_insert.q.out similarity index 59% rename from ql/src/test/results/clientpositive/ppd_multi_insert.q.out rename to ql/src/test/results/clientpositive/llap/ppd_multi_insert.q.out index e92df9bc11..6f0c154f6a 100644 --- ql/src/test/results/clientpositive/ppd_multi_insert.q.out +++ ql/src/test/results/clientpositive/llap/ppd_multi_insert.q.out @@ -56,165 +56,232 @@ POSTHOOK: Output: default@mi3@ds=2008-04-08/hr=12 POSTHOOK: Output: target/warehouse/mi4.out STAGE DEPENDENCIES: Stage-4 is a root stage - Stage-0 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-0, Stage-6, Stage-8, Stage-10, Stage-3 - Stage-6 depends on stages: Stage-4 - Stage-7 depends on stages: Stage-1, Stage-6, Stage-8, Stage-10, Stage-3 - Stage-9 depends on stages: Stage-2, Stage-6, Stage-8, Stage-10, Stage-3 - Stage-1 depends on stages: Stage-4 - Stage-8 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-4 - Stage-10 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0, Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-1, Stage-3 + Stage-2 depends on stages: Stage-5 + Stage-8 depends on stages: Stage-2, Stage-3 Stage-3 depends on stages: Stage-4 STAGE PLANS: Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mi1 - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col0 >= 100) and (_col0 < 200)) (type: boolean) - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mi2 - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col0 >= 200) and (_col0 < 300)) (type: boolean) - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mi3 - Select Operator - expressions: _col0 (type: int) - outputColumnNames: key - Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll') - keys: '2008-04-08' (type: string), '12' (type: string) - minReductionHashAggr: 0.99 - mode: hash + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 100) (type: boolean) + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mi1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 >= 100) and (_col0 < 200)) (type: boolean) + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mi2 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9885057 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 >= 200) and (_col0 < 300)) (type: boolean) + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mi3 + Select Operator + expressions: _col0 (type: int) + outputColumnNames: key + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll') + keys: '2008-04-08' (type: string), '12' (type: string) + minReductionHashAggr: 0.9885057 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: '2008-04-08' (type: string), '12' (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct) + Filter Operator + predicate: (_col0 >= 300) (type: boolean) + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0) + keys: '2008-04-08' (type: string), '12' (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (_col0 >= 300) (type: boolean) - Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Dependency Collection Stage: Stage-0 Move Operator @@ -226,53 +293,13 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.mi1 - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.mi1 - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 Stats Work Basic Stats Work: Column Stats Desc: Columns: key, value Column Types: int, string - Table: default.mi2 - - Stage: Stage-9 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key - Column Types: int - Table: default.mi3 + Table: default.mi1 Stage: Stage-1 Move Operator @@ -284,29 +311,13 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.mi2 - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.mi2 Stage: Stage-2 Move Operator @@ -321,36 +332,13 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.mi3 - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: '2008-04-08' (type: string), '12' (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) - Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0) - keys: '2008-04-08' (type: string), '12' (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-8 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key + Column Types: int + Table: default.mi3 Stage: Stage-3 Move Operator @@ -1481,165 +1469,232 @@ POSTHOOK: Output: default@mi3@ds=2008-04-08/hr=12 POSTHOOK: Output: target/warehouse/mi4.out STAGE DEPENDENCIES: Stage-4 is a root stage - Stage-0 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-0, Stage-6, Stage-8, Stage-10, Stage-3 - Stage-6 depends on stages: Stage-4 - Stage-7 depends on stages: Stage-1, Stage-6, Stage-8, Stage-10, Stage-3 - Stage-9 depends on stages: Stage-2, Stage-6, Stage-8, Stage-10, Stage-3 - Stage-1 depends on stages: Stage-4 - Stage-8 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-4 - Stage-10 depends on stages: Stage-4 + Stage-5 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-5 + Stage-6 depends on stages: Stage-0, Stage-3 + Stage-1 depends on stages: Stage-5 + Stage-7 depends on stages: Stage-1, Stage-3 + Stage-2 depends on stages: Stage-5 + Stage-8 depends on stages: Stage-2, Stage-3 Stage-3 depends on stages: Stage-4 STAGE PLANS: Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 100) (type: boolean) - Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mi1 - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col0 >= 100) and (_col0 < 200)) (type: boolean) - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mi2 - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col0 >= 200) and (_col0 < 300)) (type: boolean) - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mi3 - Select Operator - expressions: _col0 (type: int) - outputColumnNames: key - Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll') - keys: '2008-04-08' (type: string), '12' (type: string) - minReductionHashAggr: 0.99 - mode: hash + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 < 100) (type: boolean) + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mi1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 263 Data size: 24985 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 >= 100) and (_col0 < 200)) (type: boolean) + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mi2 + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 87 Data size: 8265 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.9885057 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Filter Operator + predicate: ((_col0 >= 200) and (_col0 < 300)) (type: boolean) + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 87 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mi3 + Select Operator + expressions: _col0 (type: int) + outputColumnNames: key + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll') + keys: '2008-04-08' (type: string), '12' (type: string) + minReductionHashAggr: 0.9885057 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: '2008-04-08' (type: string), '12' (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) + Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct) + Filter Operator + predicate: (_col0 >= 300) (type: boolean) + Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0) + keys: '2008-04-08' (type: string), '12' (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false + Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (_col0 >= 300) (type: boolean) - Statistics: Num rows: 263 Data size: 46814 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 263 Data size: 23933 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-5 + Dependency Collection Stage: Stage-0 Move Operator @@ -1651,53 +1706,13 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.mi1 - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.mi1 - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 Stats Work Basic Stats Work: Column Stats Desc: Columns: key, value Column Types: int, string - Table: default.mi2 - - Stage: Stage-9 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key - Column Types: int - Table: default.mi3 + Table: default.mi1 Stage: Stage-1 Move Operator @@ -1709,29 +1724,13 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.mi2 - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.mi2 Stage: Stage-2 Move Operator @@ -1746,36 +1745,13 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.mi3 - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: '2008-04-08' (type: string), '12' (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string) - Statistics: Num rows: 1 Data size: 604 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0) - keys: '2008-04-08' (type: string), '12' (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: struct), '2008-04-08' (type: string), '12' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 620 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-8 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key + Column Types: int + Table: default.mi3 Stage: Stage-3 Move Operator diff --git ql/src/test/results/clientpositive/llap/ppd_outer_join1.q.out ql/src/test/results/clientpositive/llap/ppd_outer_join1.q.out new file mode 100644 index 0000000000..8aca42d17b --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_outer_join1.q.out @@ -0,0 +1,258 @@ +PREHOOK: query: EXPLAIN + FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN + FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +PREHOOK: query: EXPLAIN + FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN + FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: FROM + src a + LEFT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 diff --git ql/src/test/results/clientpositive/ppd_outer_join2.q.out ql/src/test/results/clientpositive/llap/ppd_outer_join2.q.out similarity index 54% rename from ql/src/test/results/clientpositive/ppd_outer_join2.q.out rename to ql/src/test/results/clientpositive/llap/ppd_outer_join2.q.out index 40e1f8420c..297ad94bcf 100644 --- ql/src/test/results/clientpositive/ppd_outer_join2.q.out +++ ql/src/test/results/clientpositive/llap/ppd_outer_join2.q.out @@ -26,60 +26,74 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -261,60 +275,74 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/ppd_outer_join3.q.out ql/src/test/results/clientpositive/llap/ppd_outer_join3.q.out similarity index 54% rename from ql/src/test/results/clientpositive/ppd_outer_join3.q.out rename to ql/src/test/results/clientpositive/llap/ppd_outer_join3.q.out index 70464c2908..fe06614499 100644 --- ql/src/test/results/clientpositive/ppd_outer_join3.q.out +++ ql/src/test/results/clientpositive/llap/ppd_outer_join3.q.out @@ -26,60 +26,74 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -261,60 +275,74 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '15') and (key < '20')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '20') and (key > '15')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '15') and (key < '20')) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 86 Data size: 30616 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/ppd_outer_join4.q.out ql/src/test/results/clientpositive/llap/ppd_outer_join4.q.out similarity index 60% rename from ql/src/test/results/clientpositive/ppd_outer_join4.q.out rename to ql/src/test/results/clientpositive/llap/ppd_outer_join4.q.out index e6beceab6d..c50e8306b2 100644 --- ql/src/test/results/clientpositive/ppd_outer_join4.q.out +++ ql/src/test/results/clientpositive/llap/ppd_outer_join4.q.out @@ -28,113 +28,107 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: c - filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col2 (type: string) - TableScan - alias: b - filterExpr: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -428,113 +422,107 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: c - filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string), _col2 (type: string) - TableScan - alias: b - filterExpr: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + filterExpr: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key < '20') and (key > '15') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '15') and (key < '20') and (sqrt(key) <> 13.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: z sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 86 Data size: 22790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string), _col2 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 135 Data size: 59805 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/ppd_outer_join5.q.out ql/src/test/results/clientpositive/llap/ppd_outer_join5.q.out new file mode 100644 index 0000000000..49c0f44c5a --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_outer_join5.q.out @@ -0,0 +1,463 @@ +PREHOOK: query: create table t1_n98 (id int, key string, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t1_n98 +POSTHOOK: query: create table t1_n98 (id int, key string, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1_n98 +PREHOOK: query: create table t2_n61 (id int, key string, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t2_n61 +POSTHOOK: query: create table t2_n61 (id int, key string, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t2_n61 +PREHOOK: query: create table t3_n23 (id int, key string, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t3_n23 +POSTHOOK: query: create table t3_n23 (id int, key string, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t3_n23 +PREHOOK: query: create table t4_n12 (id int, key string, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t4_n12 +POSTHOOK: query: create table t4_n12 (id int, key string, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t4_n12 +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain select * from t1_n98 full outer join t2_n61 on t1_n98.id=t2_n61.id join t3_n23 on t2_n61.id=t3_n23.id where t3_n23.id=20 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n98 +PREHOOK: Input: default@t2_n61 +PREHOOK: Input: default@t3_n23 +#### A masked pattern was here #### +POSTHOOK: query: explain select * from t1_n98 full outer join t2_n61 on t1_n98.id=t2_n61.id join t3_n23 on t2_n61.id=t3_n23.id where t3_n23.id=20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n98 +POSTHOOK: Input: default@t2_n61 +POSTHOOK: Input: default@t3_n23 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 4 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 5 (XPROD_EDGE), Reducer 2 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n98 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 20 (type: int), key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: t2_n61 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: t3_n23 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col3 (type: string), _col4 (type: string), 20 (type: int), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t2_n61.id=t3_n23.id) where t2_n61.id=20 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n98 +PREHOOK: Input: default@t2_n61 +PREHOOK: Input: default@t3_n23 +#### A masked pattern was here #### +POSTHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t2_n61.id=t3_n23.id) where t2_n61.id=20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n98 +POSTHOOK: Input: default@t2_n61 +POSTHOOK: Input: default@t3_n23 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Map 5 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n98 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: t2_n61 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: t3_n23 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 20 (type: int), key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 20 (type: int), _col0 (type: string), _col1 (type: string), 20 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t1_n98.id=t3_n23.id) where t2_n61.id=20 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n98 +PREHOOK: Input: default@t2_n61 +PREHOOK: Input: default@t3_n23 +#### A masked pattern was here #### +POSTHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t1_n98.id=t3_n23.id) where t2_n61.id=20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n98 +POSTHOOK: Input: default@t2_n61 +POSTHOOK: Input: default@t3_n23 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Map 5 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n98 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: t2_n61 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: t3_n23 + filterExpr: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (id = 20) (type: boolean) + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 20 (type: int), key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 20 (type: int), _col0 (type: string), _col1 (type: string), 20 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: drop table t1_n98 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t1_n98 +PREHOOK: Output: default@t1_n98 +POSTHOOK: query: drop table t1_n98 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t1_n98 +POSTHOOK: Output: default@t1_n98 +PREHOOK: query: drop table t2_n61 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t2_n61 +PREHOOK: Output: default@t2_n61 +POSTHOOK: query: drop table t2_n61 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t2_n61 +POSTHOOK: Output: default@t2_n61 +PREHOOK: query: drop table t3_n23 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t3_n23 +PREHOOK: Output: default@t3_n23 +POSTHOOK: query: drop table t3_n23 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t3_n23 +POSTHOOK: Output: default@t3_n23 +PREHOOK: query: drop table t4_n12 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t4_n12 +PREHOOK: Output: default@t4_n12 +POSTHOOK: query: drop table t4_n12 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t4_n12 +POSTHOOK: Output: default@t4_n12 diff --git ql/src/test/results/clientpositive/llap/ppd_random.q.out ql/src/test/results/clientpositive/llap/ppd_random.q.out new file mode 100644 index 0000000000..cf7b0aab60 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_random.q.out @@ -0,0 +1,218 @@ +PREHOOK: query: EXPLAIN +SELECT src1.c1, src2.c4 +FROM +(SELECT src.key as c1, src.value as c2 from src ) src1 +JOIN +(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 +WHERE rand() > 0.5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT src1.c1, src2.c4 +FROM +(SELECT src.key as c1, src.value as c2 from src ) src1 +JOIN +(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 +WHERE rand() > 0.5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 262 Data size: 46636 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (rand() > 0.5D) (type: boolean) + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT src1.c1, src2.c4 +FROM +(SELECT src.key as c1, src.value as c2 from src ) src1 +JOIN +(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 +WHERE rand() > 0.5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT src1.c1, src2.c4 +FROM +(SELECT src.key as c1, src.value as c2 from src ) src1 +JOIN +(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 +ON src1.c1 = src2.c3 +WHERE rand() > 0.5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 262 Data size: 46636 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (rand() > 0.5D) (type: boolean) + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/ppd_repeated_alias.q.out ql/src/test/results/clientpositive/llap/ppd_repeated_alias.q.out new file mode 100644 index 0000000000..69416a7778 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_repeated_alias.q.out @@ -0,0 +1,468 @@ +PREHOOK: query: drop table pokes_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pokes_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table pokes2_n0 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pokes2_n0 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table pokes_n0 (foo int, bar int, blah int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pokes_n0 +POSTHOOK: query: create table pokes_n0 (foo int, bar int, blah int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pokes_n0 +PREHOOK: query: create table pokes2_n0 (foo int, bar int, blah int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pokes2_n0 +POSTHOOK: query: create table pokes2_n0 (foo int, bar int, blah int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pokes2_n0 +PREHOOK: query: explain +SELECT a.foo as foo1, b.foo as foo2, b.bar +FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b +ON a.foo=b.foo +WHERE b.bar=3 +PREHOOK: type: QUERY +PREHOOK: Input: default@pokes2_n0 +PREHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain +SELECT a.foo as foo1, b.foo as foo2, b.bar +FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b +ON a.foo=b.foo +WHERE b.bar=3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pokes2_n0 +POSTHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((bar = 3) and foo is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((bar = 3) and foo is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +SELECT * FROM + (SELECT a.foo as foo1, b.foo as foo2, b.bar + FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b + ON a.foo=b.foo) a +WHERE a.bar=3 +PREHOOK: type: QUERY +PREHOOK: Input: default@pokes2_n0 +PREHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain +SELECT * FROM + (SELECT a.foo as foo1, b.foo as foo2, b.bar + FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b + ON a.foo=b.foo) a +WHERE a.bar=3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pokes2_n0 +POSTHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((bar = 3) and foo is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((bar = 3) and foo is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +SELECT * FROM + (SELECT a.foo as foo1, b.foo as foo2, a.bar + FROM pokes_n0 a JOIN pokes2_n0 b + ON a.foo=b.foo) a +WHERE a.bar=3 +PREHOOK: type: QUERY +PREHOOK: Input: default@pokes2_n0 +PREHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain +SELECT * FROM + (SELECT a.foo as foo1, b.foo as foo2, a.bar + FROM pokes_n0 a JOIN pokes2_n0 b + ON a.foo=b.foo) a +WHERE a.bar=3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pokes2_n0 +POSTHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((bar = 3) and foo is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((bar = 3) and foo is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain select c.foo, d.bar from (select c.foo, b.bar, c.blah from pokes_n0 c left outer join pokes_n0 b on c.foo=b.foo) c left outer join pokes_n0 d where d.foo=1 and c.bar=2 +PREHOOK: type: QUERY +PREHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain select c.foo, d.bar from (select c.foo, b.bar, c.blah from pokes_n0 c left outer join pokes_n0 b on c.foo=b.foo) c left outer join pokes_n0 d where d.foo=1 and c.bar=2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@pokes_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (XPROD_EDGE), Reducer 2 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + filterExpr: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: foo is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: (((bar = 2) and foo is not null) or (foo = 1)) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((bar = 2) and foo is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: foo (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (foo = 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: bar (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: drop table pokes_n0 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pokes_n0 +PREHOOK: Output: default@pokes_n0 +POSTHOOK: query: drop table pokes_n0 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pokes_n0 +POSTHOOK: Output: default@pokes_n0 +PREHOOK: query: drop table pokes2_n0 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pokes2_n0 +PREHOOK: Output: default@pokes2_n0 +POSTHOOK: query: drop table pokes2_n0 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pokes2_n0 +POSTHOOK: Output: default@pokes2_n0 diff --git ql/src/test/results/clientpositive/llap/ppd_udf_case.q.out ql/src/test/results/clientpositive/llap/ppd_udf_case.q.out new file mode 100644 index 0000000000..cef6977dcd --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_udf_case.q.out @@ -0,0 +1,324 @@ +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key = '27') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 3 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key = '27') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 3 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + sort order: ++++ + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +27 val_27 2008-04-08 11 27 val_27 2008-04-08 11 +27 val_27 2008-04-08 11 27 val_27 2008-04-08 12 +27 val_27 2008-04-08 12 27 val_27 2008-04-08 11 +27 val_27 2008-04-08 12 27 val_27 2008-04-08 12 +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = '27') (type: boolean) + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = '27') (type: boolean) + Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + null sort order: zzzz + sort order: ++++ + Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * +FROM srcpart a JOIN srcpart b +ON a.key = b.key +WHERE a.ds = '2008-04-08' AND + b.ds = '2008-04-08' AND + CASE a.key + WHEN '27' THEN TRUE + WHEN '38' THEN FALSE + ELSE NULL + END +ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +27 val_27 2008-04-08 11 27 val_27 2008-04-08 11 +27 val_27 2008-04-08 11 27 val_27 2008-04-08 12 +27 val_27 2008-04-08 12 27 val_27 2008-04-08 11 +27 val_27 2008-04-08 12 27 val_27 2008-04-08 12 diff --git ql/src/test/results/clientpositive/llap/ppd_udf_col.q.out ql/src/test/results/clientpositive/llap/ppd_udf_col.q.out new file mode 100644 index 0000000000..6c70ca067a --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_udf_col.q.out @@ -0,0 +1,560 @@ +PREHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) = 100.0D) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: _col0, _col1 + Filter Operator + predicate: (_col1 <= 0.1D) (type: boolean) + ListSink + +PREHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 0 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) = 100.0D) (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Limit + Number of rows: 0 + Select Operator + expressions: _col0 (type: string), rand() (type: double), '4' (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) + Filter Operator + predicate: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double), (UDFToDouble(value) * 10.0D) (type: double) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) = 100.0D) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: _col0, _col1 + Filter Operator + predicate: (_col1 <= 0.1D) (type: boolean) + ListSink + +PREHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 0 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) = 100.0D) (type: boolean) + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Limit + Number of rows: 0 + Select Operator + expressions: _col0 (type: string), rand() (type: double), '4' (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) + Filter Operator + predicate: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double), (UDFToDouble(value) * 10.0D) (type: double) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (key = 100) (type: boolean) + Filter Operator + predicate: (key = 100) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: _col0, _col2 + Filter Operator + predicate: (_col2 <= 0.1D) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + TableScan + alias: src + filterExpr: (key = 100) (type: boolean) + Filter Operator + predicate: (key = 100) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: _col0, _col2 + Filter Operator + predicate: ((_col2 <= 0.1D) and (_col2 > 0.1D)) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1 + Limit + Number of rows: 20 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Filter Operator + predicate: false (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double), '4' (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) + Filter Operator + predicate: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double), (value * 10) (type: double) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (key = 100) (type: boolean) + Filter Operator + predicate: (key = 100) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: _col0, _col2 + Filter Operator + predicate: (_col2 <= 0.1D) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM +( +SELECT key, randum123 +FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a +WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 20 + Processor Tree: + TableScan + alias: src + filterExpr: (key = 100) (type: boolean) + Filter Operator + predicate: (key = 100) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: _col0, _col2 + Filter Operator + predicate: (_col2 <= 0.1D) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1 + Filter Operator + predicate: (_col1 > 0.1D) (type: boolean) + Limit + Number of rows: 20 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, h4 +FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a +WHERE a.h4 <= 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Filter Operator + predicate: ((key = 100) and false) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double) + outputColumnNames: _col0, _col2 + Filter Operator + predicate: false (type: boolean) + Select Operator + expressions: _col0 (type: string), _col2 (type: double), '4' (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT key,randum123, v10 +FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a +WHERE a.v10 <= 200 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) + Filter Operator + predicate: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) + Select Operator + expressions: key (type: string), rand() (type: double), (value * 10) (type: double) + outputColumnNames: _col0, _col2, _col3 + Filter Operator + predicate: (_col3 <= 200.0D) (type: boolean) + Select Operator + expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) + outputColumnNames: _col0, _col1, _col2 + ListSink + diff --git ql/src/test/results/clientpositive/llap/ppd_udtf.q.out ql/src/test/results/clientpositive/llap/ppd_udtf.q.out new file mode 100644 index 0000000000..d2660e5363 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_udtf.q.out @@ -0,0 +1,114 @@ +PREHOOK: query: explain +SELECT value from ( + select explode(array(key, value)) as (value) from ( + select * FROM src WHERE key > 400 + ) A +) B WHERE value < 450 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +SELECT value from ( + select explode(array(key, value)) as (value) from ( + select * FROM src WHERE key > 400 + ) A +) B WHERE value < 450 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) > 400.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) > 400.0D) (type: boolean) + Select Operator + expressions: array(key,value) (type: array) + outputColumnNames: _col0 + UDTF Operator + function name: explode + Filter Operator + predicate: (UDFToDouble(col) < 450.0D) (type: boolean) + Select Operator + expressions: col (type: string) + outputColumnNames: _col0 + ListSink + +PREHOOK: query: SELECT value from ( + select explode(array(key, value)) as (value) from ( + select * FROM src WHERE key > 400 + ) A +) B WHERE value < 450 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT value from ( + select explode(array(key, value)) as (value) from ( + select * FROM src WHERE key > 400 + ) A +) B WHERE value < 450 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +409 +401 +406 +429 +403 +417 +430 +446 +413 +417 +439 +438 +427 +437 +430 +404 +411 +431 +418 +404 +436 +409 +413 +419 +435 +401 +402 +430 +449 +401 +438 +432 +403 +406 +409 +406 +401 +424 +431 +431 +424 +438 +414 +439 +417 +444 +429 +443 +406 +401 +421 +407 +448 +414 +403 diff --git ql/src/test/results/clientpositive/ppd_union.q.out ql/src/test/results/clientpositive/llap/ppd_union.q.out similarity index 71% rename from ql/src/test/results/clientpositive/ppd_union.q.out rename to ql/src/test/results/clientpositive/llap/ppd_union.q.out index c24bf63b8e..65d770e3c4 100644 --- ql/src/test/results/clientpositive/ppd_union.q.out +++ ql/src/test/results/clientpositive/llap/ppd_union.q.out @@ -21,38 +21,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: ((key > '4') and (value > 'val_4')) (type: boolean) + Filter Operator + predicate: ((key > '4') and (value > 'val_4')) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: FROM ( FROM src select src.key, src.value WHERE src.key < '100' @@ -268,38 +252,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '4') and (value > 'val_4')) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: src + filterExpr: ((key > '4') and (value > 'val_4')) (type: boolean) + Filter Operator + predicate: ((key > '4') and (value > 'val_4')) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: FROM ( FROM src select src.key, src.value WHERE src.key < '100' diff --git ql/src/test/results/clientpositive/llap/ppd_vc.q.out ql/src/test/results/clientpositive/llap/ppd_vc.q.out new file mode 100644 index 0000000000..ebb3363172 --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_vc.q.out @@ -0,0 +1,763 @@ +PREHOOK: query: explain extended +select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds`, `hr` +FROM `default`.`srcpart` +WHERE `BLOCK__OFFSET__INSIDE__FILE` < 100 +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Partition + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Processor Tree: + TableScan + alias: srcpart + filterExpr: (BLOCK__OFFSET__INSIDE__FILE < 100L) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (BLOCK__OFFSET__INSIDE__FILE < 100L) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink + +PREHOOK: query: select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +238 val_238 2008-04-08 11 +86 val_86 2008-04-08 11 +311 val_311 2008-04-08 11 +27 val_27 2008-04-08 11 +165 val_165 2008-04-08 11 +409 val_409 2008-04-08 11 +255 val_255 2008-04-08 11 +278 val_278 2008-04-08 11 +98 val_98 2008-04-08 11 +238 val_238 2008-04-08 12 +86 val_86 2008-04-08 12 +311 val_311 2008-04-08 12 +27 val_27 2008-04-08 12 +165 val_165 2008-04-08 12 +409 val_409 2008-04-08 12 +255 val_255 2008-04-08 12 +278 val_278 2008-04-08 12 +98 val_98 2008-04-08 12 +238 val_238 2008-04-09 11 +86 val_86 2008-04-09 11 +311 val_311 2008-04-09 11 +27 val_27 2008-04-09 11 +165 val_165 2008-04-09 11 +409 val_409 2008-04-09 11 +255 val_255 2008-04-09 11 +278 val_278 2008-04-09 11 +98 val_98 2008-04-09 11 +238 val_238 2008-04-09 12 +86 val_86 2008-04-09 12 +311 val_311 2008-04-09 12 +27 val_27 2008-04-09 12 +165 val_165 2008-04-09 12 +409 val_409 2008-04-09 12 +255 val_255 2008-04-09 12 +278 val_278 2008-04-09 12 +98 val_98 2008-04-09 12 +PREHOOK: query: explain extended +select b.* from src a join + (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b + on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: explain extended +select b.* from src a join + (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b + on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `t2`.`key`, `t2`.`value`, `t2`.`ds`, `t2`.`hr`, `t2`.`BLOCK__OFFSET__INSIDE__FILE` AS `block__offset__inside__file` +FROM (SELECT `key` +FROM `default`.`src` +WHERE `key` IS NOT NULL) AS `t0` +INNER JOIN (SELECT `key`, `value`, `ds`, `hr`, `BLOCK__OFFSET__INSIDE__FILE` +FROM `default`.`srcpart` +WHERE `BLOCK__OFFSET__INSIDE__FILE` < 50 AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` +ORDER BY `t2`.`ds`, `t2`.`hr`, `t2`.`BLOCK__OFFSET__INSIDE__FILE` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Map 4 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ((BLOCK__OFFSET__INSIDE__FILE < 50L) and key is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((BLOCK__OFFSET__INSIDE__FILE < 50L) and key is not null) (type: boolean) + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 666 Data size: 368964 Basic stats: COMPLETE Column stats: PARTIAL + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 666 Data size: 368964 Basic stats: COMPLETE Column stats: PARTIAL + tag: 1 + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + auto parallelism: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [srcpart] + /srcpart/ds=2008-04-08/hr=12 [srcpart] + /srcpart/ds=2008-04-09/hr=11 [srcpart] + /srcpart/ds=2008-04-09/hr=12 [srcpart] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 + Position of Big Table: 1 + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL + Select Operator + expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col2 (type: string), _col3 (type: string), _col4 (type: bigint) + null sort order: zzz + numBuckets: -1 + sort order: +++ + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL + tag: -1 + value expressions: _col0 (type: string), _col1 (type: string) + auto parallelism: false + Reducer 3 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3,_col4 + columns.types string:string:string:string:bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select b.* from src a join + (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b + on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select b.* from src a join + (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b + on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +238 val_238 2008-04-08 11 0 +238 val_238 2008-04-08 11 0 +86 val_86 2008-04-08 11 12 +311 val_311 2008-04-08 11 22 +311 val_311 2008-04-08 11 22 +311 val_311 2008-04-08 11 22 +27 val_27 2008-04-08 11 34 +165 val_165 2008-04-08 11 44 +165 val_165 2008-04-08 11 44 +238 val_238 2008-04-08 12 0 +238 val_238 2008-04-08 12 0 +86 val_86 2008-04-08 12 12 +311 val_311 2008-04-08 12 22 +311 val_311 2008-04-08 12 22 +311 val_311 2008-04-08 12 22 +27 val_27 2008-04-08 12 34 +165 val_165 2008-04-08 12 44 +165 val_165 2008-04-08 12 44 +238 val_238 2008-04-09 11 0 +238 val_238 2008-04-09 11 0 +86 val_86 2008-04-09 11 12 +311 val_311 2008-04-09 11 22 +311 val_311 2008-04-09 11 22 +311 val_311 2008-04-09 11 22 +27 val_27 2008-04-09 11 34 +165 val_165 2008-04-09 11 44 +165 val_165 2008-04-09 11 44 +238 val_238 2008-04-09 12 0 +238 val_238 2008-04-09 12 0 +86 val_86 2008-04-09 12 12 +311 val_311 2008-04-09 12 22 +311 val_311 2008-04-09 12 22 +311 val_311 2008-04-09 12 22 +27 val_27 2008-04-09 12 34 +165 val_165 2008-04-09 12 44 +165 val_165 2008-04-09 12 44 diff --git ql/src/test/results/clientpositive/llap/ppd_windowing1.q.out ql/src/test/results/clientpositive/llap/ppd_windowing1.q.out new file mode 100644 index 0000000000..cac9b116ca --- /dev/null +++ ql/src/test/results/clientpositive/llap/ppd_windowing1.q.out @@ -0,0 +1,2321 @@ +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where cast(key as int) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where cast(key as int) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToInteger(key) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToInteger(key) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToInteger(_col0) + 2) (type: int), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where cast(key as int) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where cast(key as int) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToInteger(key) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToInteger(key) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToInteger(_col0) + 2) (type: int), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string) + outputColumnNames: sum_window_0, _col0 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col1 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string) + outputColumnNames: sum_window_0, _col0 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col1 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string) + outputColumnNames: sum_window_0, _col0 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col1 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string) + outputColumnNames: sum_window_0, _col0 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col1 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToInteger(_col1) + 2) (type: int), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key > '2') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) + outputColumnNames: sum_window_0, _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double), _col1 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string, _col2: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col2 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) > 2.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) + outputColumnNames: sum_window_0, _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double), _col1 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string, _col2: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col2 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) + outputColumnNames: sum_window_0, _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double), _col1 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string, _col2: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col2 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) + outputColumnNames: sum_window_0, _col0, _col1 + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double), _col1 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string, _col2: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS FIRST + partition by: _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_1 + arguments: _col2 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToInteger(_col1) + 2) (type: int), _col0 (type: double), sum_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, avg(value) over(partition by value) as c2 from src)r1 where key > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, avg(value) over(partition by value) as c2 from src)r1 where key > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) + outputColumnNames: sum_window_0, _col0, _col1 + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: sum_window_0 (type: double), _col0 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: double), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 227000 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: double, _col1: string, _col2: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col2 ASC NULLS FIRST + partition by: _col2 + raw input shape: + window functions: + window function definition + alias: avg_window_1 + arguments: _col2 + name: avg + window function: GenericUDAFAverageEvaluatorDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 500 Data size: 227000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: double), avg_window_1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + 2) as c1 from src)r1 where key > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + 2) as c1 from src)r1 where key > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: (UDFToDouble(key) + UDFToDouble(2)) (type: double) + null sort order: a + sort order: + + Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(2)) (type: double) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: key (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: (UDFToDouble(_col0) + UDFToDouble(2)) ASC NULLS FIRST + partition by: (UDFToDouble(_col0) + UDFToDouble(2)) + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + value) as c1 from src)r1 where key > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + value) as c1 from src)r1 where key > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: (UDFToDouble(key) + UDFToDouble(value)) (type: double) + null sort order: a + sort order: + + Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(value)) (type: double) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: key (type: string), value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: (UDFToDouble(_col0) + UDFToDouble(_col1)) ASC NULLS FIRST + partition by: (UDFToDouble(_col0) + UDFToDouble(_col1)) + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key, value) as c1 from src)r1 where (key + value) > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key, value) as c1 from src)r1 where (key + value) > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(_col0) + UDFToDouble(_col1)) > 2.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key + value) as c1 from src)r1 where (key + value) > '2' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key + value) as c1 from src)r1 where (key + value) > '2' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: (UDFToDouble(key) + UDFToDouble(value)) (type: double) + null sort order: a + sort order: + + Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(value)) (type: double) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: key (type: string), value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: (UDFToDouble(_col0) + UDFToDouble(_col1)) ASC NULLS FIRST + partition by: (UDFToDouble(_col0) + UDFToDouble(_col1)) + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(_col0) + UDFToDouble(_col1)) > 2.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+(cast(value as int)) as key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+(cast(value as int)) as key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: _col0 + name: sum + window function: GenericUDAFSumDouble + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToInteger(_col0) + UDFToInteger(_col1)) > 2) (type: boolean) + Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: (UDFToInteger(_col0) + UDFToInteger(_col1)) (type: int), _col2 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/ppd_windowing2.q.out ql/src/test/results/clientpositive/llap/ppd_windowing2.q.out similarity index 100% rename from ql/src/test/results/clientpositive/ppd_windowing2.q.out rename to ql/src/test/results/clientpositive/llap/ppd_windowing2.q.out index 0792e8fdcf..6f82153c95 100644 --- ql/src/test/results/clientpositive/ppd_windowing2.q.out +++ ql/src/test/results/clientpositive/llap/ppd_windowing2.q.out @@ -1908,10 +1908,9 @@ POSTHOOK: query: select * from (SELECT (cast(key as int))+2 as key, sum(key) ove POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -2 0.0 -2 0.0 -2 0.0 -12 10.0 +10 8.0 +100 196.0 +100 196.0 102 200.0 102 200.0 105 206.0 @@ -1919,24 +1918,24 @@ POSTHOOK: Input: default@src 106 208.0 106 208.0 107 105.0 -13 11.0 +11 9.0 113 111.0 115 226.0 115 226.0 116 114.0 118 116.0 +12 10.0 120 236.0 120 236.0 121 357.0 121 357.0 121 357.0 -14 24.0 -14 24.0 122 240.0 122 240.0 127 250.0 127 250.0 128 126.0 +13 11.0 130 384.0 130 384.0 130 384.0 @@ -1949,6 +1948,8 @@ POSTHOOK: Input: default@src 138 136.0 139 274.0 139 274.0 +14 24.0 +14 24.0 140 552.0 140 552.0 140 552.0 @@ -1959,8 +1960,6 @@ POSTHOOK: Input: default@src 148 292.0 151 298.0 151 298.0 -17 30.0 -17 30.0 152 150.0 154 304.0 154 304.0 @@ -1980,12 +1979,13 @@ POSTHOOK: Input: default@src 169 501.0 169 501.0 169 501.0 +17 30.0 +17 30.0 170 168.0 171 676.0 171 676.0 171 676.0 171 676.0 -19 17.0 172 170.0 174 344.0 174 344.0 @@ -1999,8 +1999,6 @@ POSTHOOK: Input: default@src 180 178.0 181 358.0 181 358.0 -20 36.0 -20 36.0 182 180.0 183 181.0 185 183.0 @@ -2008,8 +2006,8 @@ POSTHOOK: Input: default@src 189 561.0 189 561.0 189 561.0 +19 17.0 191 189.0 -21 19.0 192 190.0 193 382.0 193 382.0 @@ -2023,11 +2021,14 @@ POSTHOOK: Input: default@src 198 196.0 199 394.0 199 394.0 +2 0.0 +2 0.0 +2 0.0 +20 36.0 +20 36.0 201 597.0 201 597.0 201 597.0 -4 2.0 -22 20.0 202 400.0 202 400.0 203 201.0 @@ -2038,6 +2039,7 @@ POSTHOOK: Input: default@src 207 410.0 209 414.0 209 414.0 +21 19.0 210 624.0 210 624.0 210 624.0 @@ -2050,6 +2052,7 @@ POSTHOOK: Input: default@src 218 432.0 219 434.0 219 434.0 +22 20.0 220 218.0 221 438.0 221 438.0 @@ -2078,8 +2081,6 @@ POSTHOOK: Input: default@src 240 476.0 241 478.0 241 478.0 -26 48.0 -26 48.0 243 241.0 244 484.0 244 484.0 @@ -2093,16 +2094,15 @@ POSTHOOK: Input: default@src 258 512.0 258 512.0 259 257.0 +26 48.0 +26 48.0 260 258.0 -28 52.0 -28 52.0 262 260.0 264 262.0 265 263.0 267 530.0 267 530.0 268 266.0 -29 27.0 274 544.0 274 544.0 275 819.0 @@ -2114,9 +2114,10 @@ POSTHOOK: Input: default@src 279 1108.0 279 1108.0 279 1108.0 +28 52.0 +28 52.0 280 556.0 280 556.0 -30 28.0 282 560.0 282 560.0 283 562.0 @@ -2128,16 +2129,17 @@ POSTHOOK: Input: default@src 287 285.0 288 286.0 289 287.0 +29 27.0 290 576.0 290 576.0 291 289.0 293 291.0 294 292.0 298 296.0 +30 28.0 300 894.0 300 894.0 300 894.0 -32 30.0 304 302.0 307 305.0 308 306.0 @@ -2156,6 +2158,7 @@ POSTHOOK: Input: default@src 318 948.0 319 634.0 319 634.0 +32 30.0 320 954.0 320 954.0 320 954.0 @@ -2169,7 +2172,6 @@ POSTHOOK: Input: default@src 329 981.0 329 981.0 329 981.0 -35 33.0 333 662.0 333 662.0 334 332.0 @@ -2179,25 +2181,23 @@ POSTHOOK: Input: default@src 338 336.0 340 338.0 341 339.0 -36 34.0 343 341.0 344 684.0 344 684.0 346 688.0 346 688.0 347 345.0 +35 33.0 350 1740.0 350 1740.0 350 1740.0 350 1740.0 350 1740.0 -37 105.0 -37 105.0 -37 105.0 353 351.0 355 706.0 355 706.0 358 356.0 +36 34.0 362 360.0 364 362.0 366 364.0 @@ -2205,12 +2205,13 @@ POSTHOOK: Input: default@src 368 366.0 369 734.0 369 734.0 +37 105.0 +37 105.0 +37 105.0 370 368.0 371 1107.0 371 1107.0 371 1107.0 -39 74.0 -39 74.0 375 373.0 376 374.0 377 375.0 @@ -2223,6 +2224,8 @@ POSTHOOK: Input: default@src 386 1152.0 386 1152.0 388 386.0 +39 74.0 +39 74.0 391 389.0 394 392.0 395 393.0 @@ -2234,9 +2237,9 @@ POSTHOOK: Input: default@src 398 1188.0 399 794.0 399 794.0 +4 2.0 401 798.0 401 798.0 -6 4.0 402 400.0 403 2005.0 403 2005.0 @@ -2257,7 +2260,6 @@ POSTHOOK: Input: default@src 411 1227.0 411 1227.0 411 1227.0 -43 41.0 413 411.0 415 826.0 415 826.0 @@ -2268,15 +2270,13 @@ POSTHOOK: Input: default@src 419 1251.0 420 418.0 421 419.0 -44 84.0 -44 84.0 423 421.0 426 848.0 426 848.0 429 427.0 +43 41.0 431 858.0 431 858.0 -45 43.0 432 1290.0 432 1290.0 432 1290.0 @@ -2287,15 +2287,17 @@ POSTHOOK: Input: default@src 437 435.0 438 436.0 439 437.0 +44 84.0 +44 84.0 440 1314.0 440 1314.0 440 1314.0 441 878.0 441 878.0 -46 44.0 445 443.0 446 444.0 448 446.0 +45 43.0 450 448.0 451 449.0 454 452.0 @@ -2305,6 +2307,7 @@ POSTHOOK: Input: default@src 456 1362.0 457 455.0 459 457.0 +46 44.0 460 916.0 460 916.0 461 918.0 @@ -2327,7 +2330,6 @@ POSTHOOK: Input: default@src 471 2345.0 471 2345.0 471 2345.0 -49 47.0 472 470.0 474 472.0 477 475.0 @@ -2344,6 +2346,7 @@ POSTHOOK: Input: default@src 486 484.0 487 485.0 489 487.0 +49 47.0 491 1956.0 491 1956.0 491 1956.0 @@ -2360,14 +2363,12 @@ POSTHOOK: Input: default@src 500 1494.0 500 1494.0 500 1494.0 -7 15.0 -7 15.0 -7 15.0 53 102.0 53 102.0 55 53.0 56 54.0 59 57.0 +6 4.0 60 116.0 60 116.0 66 64.0 @@ -2375,6 +2376,9 @@ POSTHOOK: Input: default@src 68 66.0 69 134.0 69 134.0 +7 15.0 +7 15.0 +7 15.0 71 69.0 72 210.0 72 210.0 @@ -2386,7 +2390,6 @@ POSTHOOK: Input: default@src 78 152.0 79 77.0 80 78.0 -10 8.0 82 80.0 84 82.0 85 166.0 @@ -2396,7 +2399,6 @@ POSTHOOK: Input: default@src 87 85.0 88 86.0 89 87.0 -11 9.0 92 270.0 92 270.0 92 270.0 @@ -2406,8 +2408,6 @@ POSTHOOK: Input: default@src 98 96.0 99 194.0 99 194.0 -100 196.0 -100 196.0 PREHOOK: query: select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > '2' PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -4318,10 +4318,9 @@ POSTHOOK: query: select * from (SELECT (cast(key as int))+2 as key, sum(key) ove POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -2 0.0 -2 0.0 -2 0.0 -12 10.0 +10 8.0 +100 196.0 +100 196.0 102 200.0 102 200.0 105 206.0 @@ -4329,24 +4328,24 @@ POSTHOOK: Input: default@src 106 208.0 106 208.0 107 105.0 -13 11.0 +11 9.0 113 111.0 115 226.0 115 226.0 116 114.0 118 116.0 +12 10.0 120 236.0 120 236.0 121 357.0 121 357.0 121 357.0 -14 24.0 -14 24.0 122 240.0 122 240.0 127 250.0 127 250.0 128 126.0 +13 11.0 130 384.0 130 384.0 130 384.0 @@ -4359,6 +4358,8 @@ POSTHOOK: Input: default@src 138 136.0 139 274.0 139 274.0 +14 24.0 +14 24.0 140 552.0 140 552.0 140 552.0 @@ -4369,8 +4370,6 @@ POSTHOOK: Input: default@src 148 292.0 151 298.0 151 298.0 -17 30.0 -17 30.0 152 150.0 154 304.0 154 304.0 @@ -4390,12 +4389,13 @@ POSTHOOK: Input: default@src 169 501.0 169 501.0 169 501.0 +17 30.0 +17 30.0 170 168.0 171 676.0 171 676.0 171 676.0 171 676.0 -19 17.0 172 170.0 174 344.0 174 344.0 @@ -4409,8 +4409,6 @@ POSTHOOK: Input: default@src 180 178.0 181 358.0 181 358.0 -20 36.0 -20 36.0 182 180.0 183 181.0 185 183.0 @@ -4418,8 +4416,8 @@ POSTHOOK: Input: default@src 189 561.0 189 561.0 189 561.0 +19 17.0 191 189.0 -21 19.0 192 190.0 193 382.0 193 382.0 @@ -4433,11 +4431,14 @@ POSTHOOK: Input: default@src 198 196.0 199 394.0 199 394.0 +2 0.0 +2 0.0 +2 0.0 +20 36.0 +20 36.0 201 597.0 201 597.0 201 597.0 -4 2.0 -22 20.0 202 400.0 202 400.0 203 201.0 @@ -4448,6 +4449,7 @@ POSTHOOK: Input: default@src 207 410.0 209 414.0 209 414.0 +21 19.0 210 624.0 210 624.0 210 624.0 @@ -4460,6 +4462,7 @@ POSTHOOK: Input: default@src 218 432.0 219 434.0 219 434.0 +22 20.0 220 218.0 221 438.0 221 438.0 @@ -4488,8 +4491,6 @@ POSTHOOK: Input: default@src 240 476.0 241 478.0 241 478.0 -26 48.0 -26 48.0 243 241.0 244 484.0 244 484.0 @@ -4503,16 +4504,15 @@ POSTHOOK: Input: default@src 258 512.0 258 512.0 259 257.0 +26 48.0 +26 48.0 260 258.0 -28 52.0 -28 52.0 262 260.0 264 262.0 265 263.0 267 530.0 267 530.0 268 266.0 -29 27.0 274 544.0 274 544.0 275 819.0 @@ -4524,9 +4524,10 @@ POSTHOOK: Input: default@src 279 1108.0 279 1108.0 279 1108.0 +28 52.0 +28 52.0 280 556.0 280 556.0 -30 28.0 282 560.0 282 560.0 283 562.0 @@ -4538,16 +4539,17 @@ POSTHOOK: Input: default@src 287 285.0 288 286.0 289 287.0 +29 27.0 290 576.0 290 576.0 291 289.0 293 291.0 294 292.0 298 296.0 +30 28.0 300 894.0 300 894.0 300 894.0 -32 30.0 304 302.0 307 305.0 308 306.0 @@ -4566,6 +4568,7 @@ POSTHOOK: Input: default@src 318 948.0 319 634.0 319 634.0 +32 30.0 320 954.0 320 954.0 320 954.0 @@ -4579,7 +4582,6 @@ POSTHOOK: Input: default@src 329 981.0 329 981.0 329 981.0 -35 33.0 333 662.0 333 662.0 334 332.0 @@ -4589,25 +4591,23 @@ POSTHOOK: Input: default@src 338 336.0 340 338.0 341 339.0 -36 34.0 343 341.0 344 684.0 344 684.0 346 688.0 346 688.0 347 345.0 +35 33.0 350 1740.0 350 1740.0 350 1740.0 350 1740.0 350 1740.0 -37 105.0 -37 105.0 -37 105.0 353 351.0 355 706.0 355 706.0 358 356.0 +36 34.0 362 360.0 364 362.0 366 364.0 @@ -4615,12 +4615,13 @@ POSTHOOK: Input: default@src 368 366.0 369 734.0 369 734.0 +37 105.0 +37 105.0 +37 105.0 370 368.0 371 1107.0 371 1107.0 371 1107.0 -39 74.0 -39 74.0 375 373.0 376 374.0 377 375.0 @@ -4633,6 +4634,8 @@ POSTHOOK: Input: default@src 386 1152.0 386 1152.0 388 386.0 +39 74.0 +39 74.0 391 389.0 394 392.0 395 393.0 @@ -4644,9 +4647,9 @@ POSTHOOK: Input: default@src 398 1188.0 399 794.0 399 794.0 +4 2.0 401 798.0 401 798.0 -6 4.0 402 400.0 403 2005.0 403 2005.0 @@ -4667,7 +4670,6 @@ POSTHOOK: Input: default@src 411 1227.0 411 1227.0 411 1227.0 -43 41.0 413 411.0 415 826.0 415 826.0 @@ -4678,15 +4680,13 @@ POSTHOOK: Input: default@src 419 1251.0 420 418.0 421 419.0 -44 84.0 -44 84.0 423 421.0 426 848.0 426 848.0 429 427.0 +43 41.0 431 858.0 431 858.0 -45 43.0 432 1290.0 432 1290.0 432 1290.0 @@ -4697,15 +4697,17 @@ POSTHOOK: Input: default@src 437 435.0 438 436.0 439 437.0 +44 84.0 +44 84.0 440 1314.0 440 1314.0 440 1314.0 441 878.0 441 878.0 -46 44.0 445 443.0 446 444.0 448 446.0 +45 43.0 450 448.0 451 449.0 454 452.0 @@ -4715,6 +4717,7 @@ POSTHOOK: Input: default@src 456 1362.0 457 455.0 459 457.0 +46 44.0 460 916.0 460 916.0 461 918.0 @@ -4737,7 +4740,6 @@ POSTHOOK: Input: default@src 471 2345.0 471 2345.0 471 2345.0 -49 47.0 472 470.0 474 472.0 477 475.0 @@ -4754,6 +4756,7 @@ POSTHOOK: Input: default@src 486 484.0 487 485.0 489 487.0 +49 47.0 491 1956.0 491 1956.0 491 1956.0 @@ -4770,14 +4773,12 @@ POSTHOOK: Input: default@src 500 1494.0 500 1494.0 500 1494.0 -7 15.0 -7 15.0 -7 15.0 53 102.0 53 102.0 55 53.0 56 54.0 59 57.0 +6 4.0 60 116.0 60 116.0 66 64.0 @@ -4785,6 +4786,9 @@ POSTHOOK: Input: default@src 68 66.0 69 134.0 69 134.0 +7 15.0 +7 15.0 +7 15.0 71 69.0 72 210.0 72 210.0 @@ -4796,7 +4800,6 @@ POSTHOOK: Input: default@src 78 152.0 79 77.0 80 78.0 -10 8.0 82 80.0 84 82.0 85 166.0 @@ -4806,7 +4809,6 @@ POSTHOOK: Input: default@src 87 85.0 88 86.0 89 87.0 -11 9.0 92 270.0 92 270.0 92 270.0 @@ -4816,8 +4818,6 @@ POSTHOOK: Input: default@src 98 96.0 99 194.0 99 194.0 -100 196.0 -100 196.0 PREHOOK: query: select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > '2' PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -6224,10 +6224,9 @@ POSTHOOK: query: select * from (SELECT (cast(key as int))+2 as key, sum(key) ove POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -2 0.0 0.0 -2 0.0 0.0 -2 0.0 0.0 -12 10.0 10.0 +10 8.0 8.0 +100 196.0 196.0 +100 196.0 196.0 102 200.0 200.0 102 200.0 200.0 105 206.0 206.0 @@ -6235,24 +6234,24 @@ POSTHOOK: Input: default@src 106 208.0 208.0 106 208.0 208.0 107 105.0 105.0 -13 11.0 11.0 +11 9.0 9.0 113 111.0 111.0 115 226.0 226.0 115 226.0 226.0 116 114.0 114.0 118 116.0 116.0 +12 10.0 10.0 120 236.0 236.0 120 236.0 236.0 121 357.0 357.0 121 357.0 357.0 121 357.0 357.0 -14 24.0 24.0 -14 24.0 24.0 122 240.0 240.0 122 240.0 240.0 127 250.0 250.0 127 250.0 250.0 128 126.0 126.0 +13 11.0 11.0 130 384.0 384.0 130 384.0 384.0 130 384.0 384.0 @@ -6265,6 +6264,8 @@ POSTHOOK: Input: default@src 138 136.0 136.0 139 274.0 274.0 139 274.0 274.0 +14 24.0 24.0 +14 24.0 24.0 140 552.0 552.0 140 552.0 552.0 140 552.0 552.0 @@ -6275,8 +6276,6 @@ POSTHOOK: Input: default@src 148 292.0 292.0 151 298.0 298.0 151 298.0 298.0 -17 30.0 30.0 -17 30.0 30.0 152 150.0 150.0 154 304.0 304.0 154 304.0 304.0 @@ -6296,12 +6295,13 @@ POSTHOOK: Input: default@src 169 501.0 501.0 169 501.0 501.0 169 501.0 501.0 +17 30.0 30.0 +17 30.0 30.0 170 168.0 168.0 171 676.0 676.0 171 676.0 676.0 171 676.0 676.0 171 676.0 676.0 -19 17.0 17.0 172 170.0 170.0 174 344.0 344.0 174 344.0 344.0 @@ -6315,8 +6315,6 @@ POSTHOOK: Input: default@src 180 178.0 178.0 181 358.0 358.0 181 358.0 358.0 -20 36.0 36.0 -20 36.0 36.0 182 180.0 180.0 183 181.0 181.0 185 183.0 183.0 @@ -6324,8 +6322,8 @@ POSTHOOK: Input: default@src 189 561.0 561.0 189 561.0 561.0 189 561.0 561.0 +19 17.0 17.0 191 189.0 189.0 -21 19.0 19.0 192 190.0 190.0 193 382.0 382.0 193 382.0 382.0 @@ -6339,11 +6337,14 @@ POSTHOOK: Input: default@src 198 196.0 196.0 199 394.0 394.0 199 394.0 394.0 +2 0.0 0.0 +2 0.0 0.0 +2 0.0 0.0 +20 36.0 36.0 +20 36.0 36.0 201 597.0 597.0 201 597.0 597.0 201 597.0 597.0 -4 2.0 2.0 -22 20.0 20.0 202 400.0 400.0 202 400.0 400.0 203 201.0 201.0 @@ -6354,6 +6355,7 @@ POSTHOOK: Input: default@src 207 410.0 410.0 209 414.0 414.0 209 414.0 414.0 +21 19.0 19.0 210 624.0 624.0 210 624.0 624.0 210 624.0 624.0 @@ -6366,6 +6368,7 @@ POSTHOOK: Input: default@src 218 432.0 432.0 219 434.0 434.0 219 434.0 434.0 +22 20.0 20.0 220 218.0 218.0 221 438.0 438.0 221 438.0 438.0 @@ -6394,8 +6397,6 @@ POSTHOOK: Input: default@src 240 476.0 476.0 241 478.0 478.0 241 478.0 478.0 -26 48.0 48.0 -26 48.0 48.0 243 241.0 241.0 244 484.0 484.0 244 484.0 484.0 @@ -6409,16 +6410,15 @@ POSTHOOK: Input: default@src 258 512.0 512.0 258 512.0 512.0 259 257.0 257.0 +26 48.0 48.0 +26 48.0 48.0 260 258.0 258.0 -28 52.0 52.0 -28 52.0 52.0 262 260.0 260.0 264 262.0 262.0 265 263.0 263.0 267 530.0 530.0 267 530.0 530.0 268 266.0 266.0 -29 27.0 27.0 274 544.0 544.0 274 544.0 544.0 275 819.0 819.0 @@ -6430,9 +6430,10 @@ POSTHOOK: Input: default@src 279 1108.0 1108.0 279 1108.0 1108.0 279 1108.0 1108.0 +28 52.0 52.0 +28 52.0 52.0 280 556.0 556.0 280 556.0 556.0 -30 28.0 28.0 282 560.0 560.0 282 560.0 560.0 283 562.0 562.0 @@ -6444,16 +6445,17 @@ POSTHOOK: Input: default@src 287 285.0 285.0 288 286.0 286.0 289 287.0 287.0 +29 27.0 27.0 290 576.0 576.0 290 576.0 576.0 291 289.0 289.0 293 291.0 291.0 294 292.0 292.0 298 296.0 296.0 +30 28.0 28.0 300 894.0 894.0 300 894.0 894.0 300 894.0 894.0 -32 30.0 30.0 304 302.0 302.0 307 305.0 305.0 308 306.0 306.0 @@ -6472,6 +6474,7 @@ POSTHOOK: Input: default@src 318 948.0 948.0 319 634.0 634.0 319 634.0 634.0 +32 30.0 30.0 320 954.0 954.0 320 954.0 954.0 320 954.0 954.0 @@ -6485,7 +6488,6 @@ POSTHOOK: Input: default@src 329 981.0 981.0 329 981.0 981.0 329 981.0 981.0 -35 33.0 33.0 333 662.0 662.0 333 662.0 662.0 334 332.0 332.0 @@ -6495,25 +6497,23 @@ POSTHOOK: Input: default@src 338 336.0 336.0 340 338.0 338.0 341 339.0 339.0 -36 34.0 34.0 343 341.0 341.0 344 684.0 684.0 344 684.0 684.0 346 688.0 688.0 346 688.0 688.0 347 345.0 345.0 +35 33.0 33.0 350 1740.0 1740.0 350 1740.0 1740.0 350 1740.0 1740.0 350 1740.0 1740.0 350 1740.0 1740.0 -37 105.0 105.0 -37 105.0 105.0 -37 105.0 105.0 353 351.0 351.0 355 706.0 706.0 355 706.0 706.0 358 356.0 356.0 +36 34.0 34.0 362 360.0 360.0 364 362.0 362.0 366 364.0 364.0 @@ -6521,12 +6521,13 @@ POSTHOOK: Input: default@src 368 366.0 366.0 369 734.0 734.0 369 734.0 734.0 +37 105.0 105.0 +37 105.0 105.0 +37 105.0 105.0 370 368.0 368.0 371 1107.0 1107.0 371 1107.0 1107.0 371 1107.0 1107.0 -39 74.0 74.0 -39 74.0 74.0 375 373.0 373.0 376 374.0 374.0 377 375.0 375.0 @@ -6539,6 +6540,8 @@ POSTHOOK: Input: default@src 386 1152.0 1152.0 386 1152.0 1152.0 388 386.0 386.0 +39 74.0 74.0 +39 74.0 74.0 391 389.0 389.0 394 392.0 392.0 395 393.0 393.0 @@ -6550,9 +6553,9 @@ POSTHOOK: Input: default@src 398 1188.0 1188.0 399 794.0 794.0 399 794.0 794.0 +4 2.0 2.0 401 798.0 798.0 401 798.0 798.0 -6 4.0 4.0 402 400.0 400.0 403 2005.0 2005.0 403 2005.0 2005.0 @@ -6573,7 +6576,6 @@ POSTHOOK: Input: default@src 411 1227.0 1227.0 411 1227.0 1227.0 411 1227.0 1227.0 -43 41.0 41.0 413 411.0 411.0 415 826.0 826.0 415 826.0 826.0 @@ -6584,15 +6586,13 @@ POSTHOOK: Input: default@src 419 1251.0 1251.0 420 418.0 418.0 421 419.0 419.0 -44 84.0 84.0 -44 84.0 84.0 423 421.0 421.0 426 848.0 848.0 426 848.0 848.0 429 427.0 427.0 +43 41.0 41.0 431 858.0 858.0 431 858.0 858.0 -45 43.0 43.0 432 1290.0 1290.0 432 1290.0 1290.0 432 1290.0 1290.0 @@ -6603,15 +6603,17 @@ POSTHOOK: Input: default@src 437 435.0 435.0 438 436.0 436.0 439 437.0 437.0 +44 84.0 84.0 +44 84.0 84.0 440 1314.0 1314.0 440 1314.0 1314.0 440 1314.0 1314.0 441 878.0 878.0 441 878.0 878.0 -46 44.0 44.0 445 443.0 443.0 446 444.0 444.0 448 446.0 446.0 +45 43.0 43.0 450 448.0 448.0 451 449.0 449.0 454 452.0 452.0 @@ -6621,6 +6623,7 @@ POSTHOOK: Input: default@src 456 1362.0 1362.0 457 455.0 455.0 459 457.0 457.0 +46 44.0 44.0 460 916.0 916.0 460 916.0 916.0 461 918.0 918.0 @@ -6643,7 +6646,6 @@ POSTHOOK: Input: default@src 471 2345.0 2345.0 471 2345.0 2345.0 471 2345.0 2345.0 -49 47.0 47.0 472 470.0 470.0 474 472.0 472.0 477 475.0 475.0 @@ -6660,6 +6662,7 @@ POSTHOOK: Input: default@src 486 484.0 484.0 487 485.0 485.0 489 487.0 487.0 +49 47.0 47.0 491 1956.0 1956.0 491 1956.0 1956.0 491 1956.0 1956.0 @@ -6676,14 +6679,12 @@ POSTHOOK: Input: default@src 500 1494.0 1494.0 500 1494.0 1494.0 500 1494.0 1494.0 -7 15.0 15.0 -7 15.0 15.0 -7 15.0 15.0 53 102.0 102.0 53 102.0 102.0 55 53.0 53.0 56 54.0 54.0 59 57.0 57.0 +6 4.0 4.0 60 116.0 116.0 60 116.0 116.0 66 64.0 64.0 @@ -6691,6 +6692,9 @@ POSTHOOK: Input: default@src 68 66.0 66.0 69 134.0 134.0 69 134.0 134.0 +7 15.0 15.0 +7 15.0 15.0 +7 15.0 15.0 71 69.0 69.0 72 210.0 210.0 72 210.0 210.0 @@ -6702,7 +6706,6 @@ POSTHOOK: Input: default@src 78 152.0 152.0 79 77.0 77.0 80 78.0 78.0 -10 8.0 8.0 82 80.0 80.0 84 82.0 82.0 85 166.0 166.0 @@ -6712,7 +6715,6 @@ POSTHOOK: Input: default@src 87 85.0 85.0 88 86.0 86.0 89 87.0 87.0 -11 9.0 9.0 92 270.0 270.0 92 270.0 270.0 92 270.0 270.0 @@ -6722,8 +6724,6 @@ POSTHOOK: Input: default@src 98 96.0 96.0 99 194.0 194.0 99 194.0 194.0 -100 196.0 196.0 -100 196.0 196.0 PREHOOK: query: select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > '2' PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -8130,10 +8130,9 @@ POSTHOOK: query: select * from (SELECT (cast(key as int))+2 as key, sum(key) ove POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -2 0.0 0.0 -2 0.0 0.0 -2 0.0 0.0 -12 10.0 0.0 +10 8.0 0.0 +100 196.0 0.0 +100 196.0 0.0 102 200.0 0.0 102 200.0 0.0 105 206.0 0.0 @@ -8141,24 +8140,24 @@ POSTHOOK: Input: default@src 106 208.0 0.0 106 208.0 0.0 107 105.0 0.0 -13 11.0 0.0 +11 9.0 0.0 113 111.0 0.0 115 226.0 0.0 115 226.0 0.0 116 114.0 0.0 118 116.0 0.0 +12 10.0 0.0 120 236.0 0.0 120 236.0 0.0 121 357.0 0.0 121 357.0 0.0 121 357.0 0.0 -14 24.0 0.0 -14 24.0 0.0 122 240.0 0.0 122 240.0 0.0 127 250.0 0.0 127 250.0 0.0 128 126.0 0.0 +13 11.0 0.0 130 384.0 0.0 130 384.0 0.0 130 384.0 0.0 @@ -8171,6 +8170,8 @@ POSTHOOK: Input: default@src 138 136.0 0.0 139 274.0 0.0 139 274.0 0.0 +14 24.0 0.0 +14 24.0 0.0 140 552.0 0.0 140 552.0 0.0 140 552.0 0.0 @@ -8181,8 +8182,6 @@ POSTHOOK: Input: default@src 148 292.0 0.0 151 298.0 0.0 151 298.0 0.0 -17 30.0 0.0 -17 30.0 0.0 152 150.0 0.0 154 304.0 0.0 154 304.0 0.0 @@ -8202,12 +8201,13 @@ POSTHOOK: Input: default@src 169 501.0 0.0 169 501.0 0.0 169 501.0 0.0 +17 30.0 0.0 +17 30.0 0.0 170 168.0 0.0 171 676.0 0.0 171 676.0 0.0 171 676.0 0.0 171 676.0 0.0 -19 17.0 0.0 172 170.0 0.0 174 344.0 0.0 174 344.0 0.0 @@ -8221,8 +8221,6 @@ POSTHOOK: Input: default@src 180 178.0 0.0 181 358.0 0.0 181 358.0 0.0 -20 36.0 0.0 -20 36.0 0.0 182 180.0 0.0 183 181.0 0.0 185 183.0 0.0 @@ -8230,8 +8228,8 @@ POSTHOOK: Input: default@src 189 561.0 0.0 189 561.0 0.0 189 561.0 0.0 +19 17.0 0.0 191 189.0 0.0 -21 19.0 0.0 192 190.0 0.0 193 382.0 0.0 193 382.0 0.0 @@ -8245,11 +8243,14 @@ POSTHOOK: Input: default@src 198 196.0 0.0 199 394.0 0.0 199 394.0 0.0 +2 0.0 0.0 +2 0.0 0.0 +2 0.0 0.0 +20 36.0 0.0 +20 36.0 0.0 201 597.0 0.0 201 597.0 0.0 201 597.0 0.0 -4 2.0 0.0 -22 20.0 0.0 202 400.0 0.0 202 400.0 0.0 203 201.0 0.0 @@ -8260,6 +8261,7 @@ POSTHOOK: Input: default@src 207 410.0 0.0 209 414.0 0.0 209 414.0 0.0 +21 19.0 0.0 210 624.0 0.0 210 624.0 0.0 210 624.0 0.0 @@ -8272,6 +8274,7 @@ POSTHOOK: Input: default@src 218 432.0 0.0 219 434.0 0.0 219 434.0 0.0 +22 20.0 0.0 220 218.0 0.0 221 438.0 0.0 221 438.0 0.0 @@ -8300,8 +8303,6 @@ POSTHOOK: Input: default@src 240 476.0 0.0 241 478.0 0.0 241 478.0 0.0 -26 48.0 0.0 -26 48.0 0.0 243 241.0 0.0 244 484.0 0.0 244 484.0 0.0 @@ -8315,16 +8316,15 @@ POSTHOOK: Input: default@src 258 512.0 0.0 258 512.0 0.0 259 257.0 0.0 +26 48.0 0.0 +26 48.0 0.0 260 258.0 0.0 -28 52.0 0.0 -28 52.0 0.0 262 260.0 0.0 264 262.0 0.0 265 263.0 0.0 267 530.0 0.0 267 530.0 0.0 268 266.0 0.0 -29 27.0 0.0 274 544.0 0.0 274 544.0 0.0 275 819.0 0.0 @@ -8336,9 +8336,10 @@ POSTHOOK: Input: default@src 279 1108.0 0.0 279 1108.0 0.0 279 1108.0 0.0 +28 52.0 0.0 +28 52.0 0.0 280 556.0 0.0 280 556.0 0.0 -30 28.0 0.0 282 560.0 0.0 282 560.0 0.0 283 562.0 0.0 @@ -8350,16 +8351,17 @@ POSTHOOK: Input: default@src 287 285.0 0.0 288 286.0 0.0 289 287.0 0.0 +29 27.0 0.0 290 576.0 0.0 290 576.0 0.0 291 289.0 0.0 293 291.0 0.0 294 292.0 0.0 298 296.0 0.0 +30 28.0 0.0 300 894.0 0.0 300 894.0 0.0 300 894.0 0.0 -32 30.0 0.0 304 302.0 0.0 307 305.0 0.0 308 306.0 0.0 @@ -8378,6 +8380,7 @@ POSTHOOK: Input: default@src 318 948.0 0.0 319 634.0 0.0 319 634.0 0.0 +32 30.0 0.0 320 954.0 0.0 320 954.0 0.0 320 954.0 0.0 @@ -8391,7 +8394,6 @@ POSTHOOK: Input: default@src 329 981.0 0.0 329 981.0 0.0 329 981.0 0.0 -35 33.0 0.0 333 662.0 0.0 333 662.0 0.0 334 332.0 0.0 @@ -8401,25 +8403,23 @@ POSTHOOK: Input: default@src 338 336.0 0.0 340 338.0 0.0 341 339.0 0.0 -36 34.0 0.0 343 341.0 0.0 344 684.0 0.0 344 684.0 0.0 346 688.0 0.0 346 688.0 0.0 347 345.0 0.0 +35 33.0 0.0 350 1740.0 0.0 350 1740.0 0.0 350 1740.0 0.0 350 1740.0 0.0 350 1740.0 0.0 -37 105.0 0.0 -37 105.0 0.0 -37 105.0 0.0 353 351.0 0.0 355 706.0 0.0 355 706.0 0.0 358 356.0 0.0 +36 34.0 0.0 362 360.0 0.0 364 362.0 0.0 366 364.0 0.0 @@ -8427,12 +8427,13 @@ POSTHOOK: Input: default@src 368 366.0 0.0 369 734.0 0.0 369 734.0 0.0 +37 105.0 0.0 +37 105.0 0.0 +37 105.0 0.0 370 368.0 0.0 371 1107.0 0.0 371 1107.0 0.0 371 1107.0 0.0 -39 74.0 0.0 -39 74.0 0.0 375 373.0 0.0 376 374.0 0.0 377 375.0 0.0 @@ -8445,6 +8446,8 @@ POSTHOOK: Input: default@src 386 1152.0 0.0 386 1152.0 0.0 388 386.0 0.0 +39 74.0 0.0 +39 74.0 0.0 391 389.0 0.0 394 392.0 0.0 395 393.0 0.0 @@ -8456,9 +8459,9 @@ POSTHOOK: Input: default@src 398 1188.0 0.0 399 794.0 0.0 399 794.0 0.0 +4 2.0 0.0 401 798.0 0.0 401 798.0 0.0 -6 4.0 0.0 402 400.0 0.0 403 2005.0 0.0 403 2005.0 0.0 @@ -8479,7 +8482,6 @@ POSTHOOK: Input: default@src 411 1227.0 0.0 411 1227.0 0.0 411 1227.0 0.0 -43 41.0 0.0 413 411.0 0.0 415 826.0 0.0 415 826.0 0.0 @@ -8490,15 +8492,13 @@ POSTHOOK: Input: default@src 419 1251.0 0.0 420 418.0 0.0 421 419.0 0.0 -44 84.0 0.0 -44 84.0 0.0 423 421.0 0.0 426 848.0 0.0 426 848.0 0.0 429 427.0 0.0 +43 41.0 0.0 431 858.0 0.0 431 858.0 0.0 -45 43.0 0.0 432 1290.0 0.0 432 1290.0 0.0 432 1290.0 0.0 @@ -8509,15 +8509,17 @@ POSTHOOK: Input: default@src 437 435.0 0.0 438 436.0 0.0 439 437.0 0.0 +44 84.0 0.0 +44 84.0 0.0 440 1314.0 0.0 440 1314.0 0.0 440 1314.0 0.0 441 878.0 0.0 441 878.0 0.0 -46 44.0 0.0 445 443.0 0.0 446 444.0 0.0 448 446.0 0.0 +45 43.0 0.0 450 448.0 0.0 451 449.0 0.0 454 452.0 0.0 @@ -8527,6 +8529,7 @@ POSTHOOK: Input: default@src 456 1362.0 0.0 457 455.0 0.0 459 457.0 0.0 +46 44.0 0.0 460 916.0 0.0 460 916.0 0.0 461 918.0 0.0 @@ -8549,7 +8552,6 @@ POSTHOOK: Input: default@src 471 2345.0 0.0 471 2345.0 0.0 471 2345.0 0.0 -49 47.0 0.0 472 470.0 0.0 474 472.0 0.0 477 475.0 0.0 @@ -8566,6 +8568,7 @@ POSTHOOK: Input: default@src 486 484.0 0.0 487 485.0 0.0 489 487.0 0.0 +49 47.0 0.0 491 1956.0 0.0 491 1956.0 0.0 491 1956.0 0.0 @@ -8582,14 +8585,12 @@ POSTHOOK: Input: default@src 500 1494.0 0.0 500 1494.0 0.0 500 1494.0 0.0 -7 15.0 0.0 -7 15.0 0.0 -7 15.0 0.0 53 102.0 0.0 53 102.0 0.0 55 53.0 0.0 56 54.0 0.0 59 57.0 0.0 +6 4.0 0.0 60 116.0 0.0 60 116.0 0.0 66 64.0 0.0 @@ -8597,6 +8598,9 @@ POSTHOOK: Input: default@src 68 66.0 0.0 69 134.0 0.0 69 134.0 0.0 +7 15.0 0.0 +7 15.0 0.0 +7 15.0 0.0 71 69.0 0.0 72 210.0 0.0 72 210.0 0.0 @@ -8608,7 +8612,6 @@ POSTHOOK: Input: default@src 78 152.0 0.0 79 77.0 0.0 80 78.0 0.0 -10 8.0 0.0 82 80.0 0.0 84 82.0 0.0 85 166.0 0.0 @@ -8618,7 +8621,6 @@ POSTHOOK: Input: default@src 87 85.0 0.0 88 86.0 0.0 89 87.0 0.0 -11 9.0 0.0 92 270.0 0.0 92 270.0 0.0 92 270.0 0.0 @@ -8628,8 +8630,6 @@ POSTHOOK: Input: default@src 98 96.0 0.0 99 194.0 0.0 99 194.0 0.0 -100 196.0 0.0 -100 196.0 0.0 PREHOOK: query: select * from (SELECT key, sum(key) over(partition by key,value) as c1, avg(value) over(partition by value) as c2 from src)r1 where key > '2' PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -9027,76 +9027,7 @@ POSTHOOK: query: select * from (SELECT key, sum(key) over(partition by key + 2) POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -4 4.0 -5 15.0 -5 15.0 -5 15.0 -8 8.0 -9 9.0 20 20.0 -24 48.0 -24 48.0 -26 52.0 -26 52.0 -27 27.0 -28 28.0 -30 30.0 -33 33.0 -34 34.0 -35 105.0 -35 105.0 -35 105.0 -37 74.0 -37 74.0 -41 41.0 -42 84.0 -42 84.0 -43 43.0 -44 44.0 -47 47.0 -51 102.0 -51 102.0 -53 53.0 -54 54.0 -57 57.0 -58 116.0 -58 116.0 -64 64.0 -65 65.0 -66 66.0 -67 134.0 -67 134.0 -69 69.0 -70 210.0 -70 210.0 -70 210.0 -72 144.0 -72 144.0 -74 74.0 -76 152.0 -76 152.0 -77 77.0 -78 78.0 -80 80.0 -82 82.0 -83 166.0 -83 166.0 -84 168.0 -84 168.0 -85 85.0 -86 86.0 -87 87.0 -90 270.0 -90 270.0 -90 270.0 -92 92.0 -95 190.0 -95 190.0 -96 96.0 -97 194.0 -97 194.0 -98 196.0 -98 196.0 200 400.0 200 400.0 201 201.0 @@ -9147,6 +9078,8 @@ POSTHOOK: Input: default@src 238 476.0 239 478.0 239 478.0 +24 48.0 +24 48.0 241 241.0 242 484.0 242 484.0 @@ -9161,12 +9094,15 @@ POSTHOOK: Input: default@src 256 512.0 257 257.0 258 258.0 +26 52.0 +26 52.0 260 260.0 262 262.0 263 263.0 265 530.0 265 530.0 266 266.0 +27 27.0 272 544.0 272 544.0 273 819.0 @@ -9180,6 +9116,7 @@ POSTHOOK: Input: default@src 277 1108.0 278 556.0 278 556.0 +28 28.0 280 560.0 280 560.0 281 562.0 @@ -9200,6 +9137,7 @@ POSTHOOK: Input: default@src 298 894.0 298 894.0 298 894.0 +30 30.0 302 302.0 305 305.0 306 306.0 @@ -9231,6 +9169,7 @@ POSTHOOK: Input: default@src 327 981.0 327 981.0 327 981.0 +33 33.0 331 662.0 331 662.0 332 332.0 @@ -9240,6 +9179,7 @@ POSTHOOK: Input: default@src 336 336.0 338 338.0 339 339.0 +34 34.0 341 341.0 342 684.0 342 684.0 @@ -9251,6 +9191,9 @@ POSTHOOK: Input: default@src 348 1740.0 348 1740.0 348 1740.0 +35 105.0 +35 105.0 +35 105.0 351 351.0 353 706.0 353 706.0 @@ -9266,6 +9209,8 @@ POSTHOOK: Input: default@src 369 1107.0 369 1107.0 369 1107.0 +37 74.0 +37 74.0 373 373.0 374 374.0 375 375.0 @@ -9291,6 +9236,7 @@ POSTHOOK: Input: default@src 397 794.0 399 798.0 399 798.0 +4 4.0 400 400.0 401 2005.0 401 2005.0 @@ -9311,6 +9257,7 @@ POSTHOOK: Input: default@src 409 1227.0 409 1227.0 409 1227.0 +41 41.0 411 411.0 413 826.0 413 826.0 @@ -9321,12 +9268,15 @@ POSTHOOK: Input: default@src 417 1251.0 418 418.0 419 419.0 +42 84.0 +42 84.0 421 421.0 424 848.0 424 848.0 427 427.0 429 858.0 429 858.0 +43 43.0 430 1290.0 430 1290.0 430 1290.0 @@ -9342,6 +9292,7 @@ POSTHOOK: Input: default@src 438 1314.0 439 878.0 439 878.0 +44 44.0 443 443.0 444 444.0 446 446.0 @@ -9376,6 +9327,7 @@ POSTHOOK: Input: default@src 469 2345.0 469 2345.0 469 2345.0 +47 47.0 470 470.0 472 472.0 475 475.0 @@ -9408,6 +9360,54 @@ POSTHOOK: Input: default@src 498 1494.0 498 1494.0 498 1494.0 +5 15.0 +5 15.0 +5 15.0 +51 102.0 +51 102.0 +53 53.0 +54 54.0 +57 57.0 +58 116.0 +58 116.0 +64 64.0 +65 65.0 +66 66.0 +67 134.0 +67 134.0 +69 69.0 +70 210.0 +70 210.0 +70 210.0 +72 144.0 +72 144.0 +74 74.0 +76 152.0 +76 152.0 +77 77.0 +78 78.0 +8 8.0 +80 80.0 +82 82.0 +83 166.0 +83 166.0 +84 168.0 +84 168.0 +85 85.0 +86 86.0 +87 87.0 +9 9.0 +90 270.0 +90 270.0 +90 270.0 +92 92.0 +95 190.0 +95 190.0 +96 96.0 +97 194.0 +97 194.0 +98 196.0 +98 196.0 PREHOOK: query: select * from (SELECT key, sum(key) over(partition by key + value) as c1 from src)r1 where key > '2' PREHOOK: type: QUERY PREHOOK: Input: default@src @@ -9416,387 +9416,387 @@ POSTHOOK: query: select * from (SELECT key, sum(key) over(partition by key + val POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -97 130091.0 +20 130091.0 200 130091.0 -400 130091.0 -403 130091.0 -90 130091.0 -222 130091.0 -477 130091.0 -414 130091.0 -307 130091.0 -348 130091.0 -448 130091.0 -37 130091.0 -28 130091.0 -84 130091.0 -315 130091.0 -469 130091.0 -97 130091.0 -344 130091.0 -281 130091.0 -273 130091.0 -348 130091.0 -285 130091.0 -362 130091.0 -458 130091.0 -498 130091.0 -341 130091.0 -9 130091.0 -298 130091.0 -492 130091.0 -462 130091.0 -379 130091.0 -384 130091.0 -67 130091.0 -26 130091.0 -256 130091.0 -384 130091.0 -407 130091.0 -421 130091.0 -401 130091.0 -375 130091.0 -454 130091.0 -406 130091.0 -233 130091.0 -462 130091.0 -214 130091.0 -353 130091.0 -83 130091.0 -480 130091.0 -265 130091.0 -249 130091.0 -207 130091.0 -460 130091.0 -493 130091.0 -333 130091.0 -317 130091.0 -310 130091.0 -468 130091.0 -478 130091.0 -230 130091.0 -277 130091.0 -325 130091.0 -323 130091.0 -443 130091.0 -429 130091.0 -444 130091.0 -417 130091.0 -305 130091.0 -479 130091.0 -248 130091.0 -360 130091.0 -439 130091.0 -237 130091.0 -491 130091.0 200 130091.0 -414 130091.0 -438 130091.0 -70 130091.0 -255 130091.0 -351 130091.0 -24 130091.0 -291 130091.0 -480 130091.0 -397 130091.0 -70 130091.0 -5 130091.0 -382 130091.0 -424 130091.0 -431 130091.0 -298 130091.0 -478 130091.0 -454 130091.0 -431 130091.0 -217 130091.0 201 130091.0 -396 130091.0 -424 130091.0 -348 130091.0 -262 130091.0 +202 130091.0 203 130091.0 -90 130091.0 -258 130091.0 -401 130091.0 -406 130091.0 -409 130091.0 -406 130091.0 -257 130091.0 -53 130091.0 -483 130091.0 -403 130091.0 -366 130091.0 -466 130091.0 -335 130091.0 -321 130091.0 -44 130091.0 -80 130091.0 -235 130091.0 -331 130091.0 -283 130091.0 -35 130091.0 -280 130091.0 -463 130091.0 -469 130091.0 +203 130091.0 +205 130091.0 +205 130091.0 +207 130091.0 +207 130091.0 +208 130091.0 +208 130091.0 +208 130091.0 +209 130091.0 +209 130091.0 +213 130091.0 +213 130091.0 +214 130091.0 +216 130091.0 +216 130091.0 +217 130091.0 +217 130091.0 +218 130091.0 +219 130091.0 +219 130091.0 +221 130091.0 +221 130091.0 +222 130091.0 +223 130091.0 +223 130091.0 +224 130091.0 +224 130091.0 +226 130091.0 +228 130091.0 229 130091.0 -316 130091.0 -202 130091.0 -432 130091.0 -467 130091.0 -438 130091.0 +229 130091.0 +230 130091.0 +230 130091.0 +230 130091.0 +230 130091.0 +230 130091.0 +233 130091.0 +233 130091.0 +235 130091.0 +237 130091.0 +237 130091.0 +238 130091.0 +238 130091.0 +239 130091.0 +239 130091.0 +24 130091.0 +24 130091.0 +241 130091.0 +242 130091.0 +242 130091.0 244 130091.0 -5 130091.0 -288 130091.0 -401 130091.0 -480 130091.0 -487 130091.0 -70 130091.0 -263 130091.0 +247 130091.0 +248 130091.0 +249 130091.0 +252 130091.0 +255 130091.0 +255 130091.0 256 130091.0 -223 130091.0 -485 130091.0 -239 130091.0 -219 130091.0 +256 130091.0 +257 130091.0 +258 130091.0 +26 130091.0 +26 130091.0 +260 130091.0 +262 130091.0 +263 130091.0 +265 130091.0 +265 130091.0 +266 130091.0 +27 130091.0 +272 130091.0 +272 130091.0 +273 130091.0 +273 130091.0 +273 130091.0 274 130091.0 -344 130091.0 -367 130091.0 -216 130091.0 +275 130091.0 +277 130091.0 +277 130091.0 +277 130091.0 +277 130091.0 +278 130091.0 +278 130091.0 +28 130091.0 +280 130091.0 +280 130091.0 +281 130091.0 +281 130091.0 +282 130091.0 +282 130091.0 +283 130091.0 +284 130091.0 +285 130091.0 +286 130091.0 +287 130091.0 +288 130091.0 +288 130091.0 +289 130091.0 +291 130091.0 +292 130091.0 296 130091.0 -368 130091.0 -33 130091.0 -230 130091.0 -69 130091.0 -342 130091.0 -74 130091.0 -76 130091.0 -468 130091.0 -64 130091.0 -209 130091.0 +298 130091.0 +298 130091.0 +298 130091.0 30 130091.0 -453 130091.0 -228 130091.0 -218 130091.0 -449 130091.0 -492 130091.0 -223 130091.0 -41 130091.0 -76 130091.0 -78 130091.0 -458 130091.0 -489 130091.0 -430 130091.0 +302 130091.0 +305 130091.0 +306 130091.0 +307 130091.0 +307 130091.0 +308 130091.0 +309 130091.0 +309 130091.0 +310 130091.0 +311 130091.0 +311 130091.0 +311 130091.0 +315 130091.0 +316 130091.0 +316 130091.0 +316 130091.0 +317 130091.0 +317 130091.0 +318 130091.0 +318 130091.0 +318 130091.0 +321 130091.0 321 130091.0 -42 130091.0 -498 130091.0 322 130091.0 -472 130091.0 -233 130091.0 -229 130091.0 -34 130091.0 -95 130091.0 +322 130091.0 +323 130091.0 +325 130091.0 +325 130091.0 +327 130091.0 +327 130091.0 +327 130091.0 +33 130091.0 +331 130091.0 +331 130091.0 +332 130091.0 +333 130091.0 +333 130091.0 +335 130091.0 336 130091.0 +338 130091.0 +339 130091.0 +34 130091.0 +341 130091.0 +342 130091.0 +342 130091.0 +344 130091.0 +344 130091.0 +345 130091.0 +348 130091.0 +348 130091.0 +348 130091.0 +348 130091.0 +348 130091.0 35 130091.0 -58 130091.0 -395 130091.0 -317 130091.0 -396 130091.0 -402 130091.0 -497 130091.0 -5 130091.0 -226 130091.0 -452 130091.0 -242 130091.0 -401 130091.0 -331 130091.0 -272 130091.0 -392 130091.0 +35 130091.0 +35 130091.0 +351 130091.0 +353 130091.0 +353 130091.0 +356 130091.0 +360 130091.0 +362 130091.0 +364 130091.0 +365 130091.0 +366 130091.0 +367 130091.0 +367 130091.0 +368 130091.0 369 130091.0 -242 130091.0 -327 130091.0 +369 130091.0 +369 130091.0 +37 130091.0 +37 130091.0 +373 130091.0 +374 130091.0 +375 130091.0 +377 130091.0 +378 130091.0 +379 130091.0 +382 130091.0 +382 130091.0 +384 130091.0 +384 130091.0 +384 130091.0 +386 130091.0 389 130091.0 -309 130091.0 -224 130091.0 -306 130091.0 -273 130091.0 -277 130091.0 -435 130091.0 -307 130091.0 -90 130091.0 -72 130091.0 -419 130091.0 -238 130091.0 -282 130091.0 +392 130091.0 +393 130091.0 +394 130091.0 395 130091.0 -364 130091.0 -87 130091.0 -490 130091.0 -77 130091.0 -85 130091.0 -413 130091.0 -316 130091.0 -369 130091.0 -470 130091.0 -409 130091.0 -318 130091.0 -318 130091.0 -282 130091.0 -98 130091.0 -457 130091.0 -481 130091.0 -288 130091.0 -95 130091.0 -308 130091.0 -468 130091.0 -469 130091.0 -436 130091.0 -43 130091.0 +395 130091.0 +396 130091.0 +396 130091.0 +396 130091.0 +397 130091.0 +397 130091.0 +399 130091.0 +399 130091.0 +4 130091.0 +400 130091.0 +401 130091.0 +401 130091.0 +401 130091.0 +401 130091.0 +401 130091.0 +402 130091.0 +403 130091.0 +403 130091.0 +403 130091.0 404 130091.0 -51 130091.0 -205 130091.0 -230 130091.0 -327 130091.0 -26 130091.0 -96 130091.0 +404 130091.0 +406 130091.0 +406 130091.0 +406 130091.0 +406 130091.0 +407 130091.0 +409 130091.0 +409 130091.0 +409 130091.0 +41 130091.0 +411 130091.0 +413 130091.0 +413 130091.0 +414 130091.0 +414 130091.0 +417 130091.0 +417 130091.0 +417 130091.0 418 130091.0 -298 130091.0 -454 130091.0 -393 130091.0 -468 130091.0 -322 130091.0 -496 130091.0 +419 130091.0 +42 130091.0 42 130091.0 +421 130091.0 +424 130091.0 +424 130091.0 +427 130091.0 +429 130091.0 +429 130091.0 +43 130091.0 +430 130091.0 +430 130091.0 +430 130091.0 +431 130091.0 +431 130091.0 431 130091.0 +432 130091.0 +435 130091.0 +436 130091.0 +437 130091.0 +438 130091.0 +438 130091.0 +438 130091.0 +439 130091.0 +439 130091.0 +44 130091.0 +443 130091.0 +444 130091.0 +446 130091.0 +448 130091.0 +449 130091.0 +452 130091.0 +453 130091.0 +454 130091.0 +454 130091.0 +454 130091.0 +455 130091.0 +457 130091.0 +458 130091.0 +458 130091.0 +459 130091.0 +459 130091.0 +460 130091.0 +462 130091.0 +462 130091.0 +463 130091.0 463 130091.0 -24 130091.0 -348 130091.0 -208 130091.0 -230 130091.0 -411 130091.0 -8 130091.0 -58 130091.0 466 130091.0 -348 130091.0 -84 130091.0 -217 130091.0 -272 130091.0 -373 130091.0 -353 130091.0 -489 130091.0 -384 130091.0 -404 130091.0 -260 130091.0 -67 130091.0 -230 130091.0 -284 130091.0 -333 130091.0 -83 130091.0 -241 130091.0 -275 130091.0 -311 130091.0 -332 130091.0 -318 130091.0 -65 130091.0 -221 130091.0 -289 130091.0 -278 130091.0 -430 130091.0 -216 130091.0 -213 130091.0 -239 130091.0 -51 130091.0 -459 130091.0 -54 130091.0 -286 130091.0 +466 130091.0 +466 130091.0 +467 130091.0 +468 130091.0 +468 130091.0 +468 130091.0 +468 130091.0 +469 130091.0 +469 130091.0 +469 130091.0 +469 130091.0 469 130091.0 -437 130091.0 -386 130091.0 -498 130091.0 -382 130091.0 -399 130091.0 -356 130091.0 -208 130091.0 -277 130091.0 -427 130091.0 -35 130091.0 -280 130091.0 -4 130091.0 -72 130091.0 47 130091.0 -92 130091.0 -221 130091.0 -378 130091.0 -489 130091.0 -20 130091.0 -345 130091.0 -438 130091.0 -205 130091.0 -302 130091.0 -57 130091.0 -316 130091.0 -311 130091.0 -455 130091.0 -339 130091.0 -203 130091.0 +470 130091.0 +472 130091.0 475 130091.0 -325 130091.0 -367 130091.0 -342 130091.0 -439 130091.0 -266 130091.0 -365 130091.0 -309 130091.0 -397 130091.0 -377 130091.0 +477 130091.0 +478 130091.0 +478 130091.0 +479 130091.0 +480 130091.0 +480 130091.0 +480 130091.0 +481 130091.0 +482 130091.0 +483 130091.0 +484 130091.0 +485 130091.0 +487 130091.0 489 130091.0 -417 130091.0 -247 130091.0 -396 130091.0 -399 130091.0 -208 130091.0 -466 130091.0 -207 130091.0 +489 130091.0 +489 130091.0 +489 130091.0 +490 130091.0 +491 130091.0 +492 130091.0 +492 130091.0 +493 130091.0 494 130091.0 -413 130091.0 -482 130091.0 -237 130091.0 -394 130091.0 -459 130091.0 -446 130091.0 -338 130091.0 -287 130091.0 -219 130091.0 -292 130091.0 -252 130091.0 -430 130091.0 -417 130091.0 -403 130091.0 -82 130091.0 -209 130091.0 -277 130091.0 -281 130091.0 -327 130091.0 -37 130091.0 495 130091.0 -469 130091.0 -374 130091.0 -429 130091.0 -406 130091.0 -213 130091.0 +496 130091.0 +497 130091.0 +498 130091.0 +498 130091.0 +498 130091.0 +5 130091.0 +5 130091.0 +5 130091.0 +51 130091.0 +51 130091.0 +53 130091.0 +54 130091.0 +57 130091.0 +58 130091.0 +58 130091.0 +64 130091.0 +65 130091.0 66 130091.0 -369 130091.0 -224 130091.0 -273 130091.0 -401 130091.0 -265 130091.0 -484 130091.0 -98 130091.0 -278 130091.0 -255 130091.0 -409 130091.0 -27 130091.0 -311 130091.0 +67 130091.0 +67 130091.0 +69 130091.0 +70 130091.0 +70 130091.0 +70 130091.0 +72 130091.0 +72 130091.0 +74 130091.0 +76 130091.0 +76 130091.0 +77 130091.0 +78 130091.0 +8 130091.0 +80 130091.0 +82 130091.0 +83 130091.0 +83 130091.0 +84 130091.0 +84 130091.0 +85 130091.0 86 130091.0 -238 130091.0 +87 130091.0 +9 130091.0 +90 130091.0 +90 130091.0 +90 130091.0 +92 130091.0 +95 130091.0 +95 130091.0 +96 130091.0 +97 130091.0 +97 130091.0 +98 130091.0 +98 130091.0 PREHOOK: query: select * from (SELECT key, value, sum(key) over(partition by key, value) as c1 from src)r1 where (key + value) > '2' PREHOOK: type: QUERY PREHOOK: Input: default@src diff --git ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out ql/src/test/results/clientpositive/llap/ppr_allchildsarenull.q.out similarity index 76% rename from ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out rename to ql/src/test/results/clientpositive/llap/ppr_allchildsarenull.q.out index ad09fdf5ab..0061e60fd4 100644 --- ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out +++ ql/src/test/results/clientpositive/llap/ppr_allchildsarenull.q.out @@ -28,57 +28,14 @@ OPTIMIZED SQL: SELECT CAST(`key` AS INTEGER) AS `user_id`, `value` FROM `default`.`srcpart` WHERE (`value` LIKE 'aaa%' OR `value` LIKE 'vvv%') AND `ds` = '2008-04-08' STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: (((value like 'aaa%') or (value like 'vvv%')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(key) (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -125,9 +82,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart -#### A masked pattern was here #### Partition - base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -174,15 +129,18 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: srcpart + filterExpr: (((value like 'aaa%') or (value like 'vvv%')) and (ds = '2008-04-08')) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: SELECT CAST(key AS INT) AS user_id, value @@ -242,56 +200,14 @@ OPTIMIZED SQL: SELECT CAST(`key` AS INTEGER) AS `user_id`, `value` FROM `default`.`srcpart` WHERE (`value` LIKE 'aaa%' OR `value` LIKE 'vvv%') AND `ds` = '2008-04-08' STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((value like 'aaa%') or (value like 'vvv%')) and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(key) (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 190000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2000 Data size: 190000 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -338,9 +254,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart -#### A masked pattern was here #### Partition - base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -387,9 +301,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart -#### A masked pattern was here #### Partition - base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -436,9 +348,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart -#### A masked pattern was here #### Partition - base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -485,17 +395,17 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: srcpart + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (((value like 'aaa%') or (value like 'vvv%')) and (ds = '2008-04-08')) (type: boolean) + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: SELECT CAST(key AS INT) AS user_id, value diff --git ql/src/test/results/clientpositive/ppr_pushdown3.q.out ql/src/test/results/clientpositive/llap/ppr_pushdown3.q.out similarity index 97% rename from ql/src/test/results/clientpositive/ppr_pushdown3.q.out rename to ql/src/test/results/clientpositive/llap/ppr_pushdown3.q.out index 83daa40df7..91526e5f18 100644 --- ql/src/test/results/clientpositive/ppr_pushdown3.q.out +++ ql/src/test/results/clientpositive/llap/ppr_pushdown3.q.out @@ -15,38 +15,22 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: srcpart + filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) < 10.0D) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: select * from srcpart where key < 10 PREHOOK: type: QUERY @@ -130,11 +114,9 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select * from srcpart @@ -2179,11 +2161,9 @@ STAGE PLANS: Processor Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: select key from srcpart diff --git ql/src/test/results/clientpositive/print_header.q.out ql/src/test/results/clientpositive/llap/print_header.q.out similarity index 64% rename from ql/src/test/results/clientpositive/print_header.q.out rename to ql/src/test/results/clientpositive/llap/print_header.q.out index 48d7455196..f35bacae78 100644 --- ql/src/test/results/clientpositive/print_header.q.out +++ ql/src/test/results/clientpositive/llap/print_header.q.out @@ -1,21 +1,19 @@ -Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 - LIMIT 10 + src2.key as k2, src2.value as v2 + FROM (SELECT * FROM src WHERE src.key < 10) src1 + JOIN (SELECT * FROM src WHERE src.key < 10) src2 +ORDER BY k1, v1, k2, v2 + LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 - LIMIT 10 + src2.key as k2, src2.value as v2 + FROM (SELECT * FROM src WHERE src.key < 10) src1 + JOIN (SELECT * FROM src WHERE src.key < 10) src2 +ORDER BY k1, v1, k2, v2 + LIMIT 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### @@ -30,11 +28,11 @@ k1 v1 k2 v2 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 2 val_2 -PREHOOK: query: SELECT src.key, sum(substr(src.value,5)) FROM src GROUP BY src.key LIMIT 10 +PREHOOK: query: SELECT src.key, sum(substr(src.value,5)) FROM src GROUP BY src.key ORDER BY src.key LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: SELECT src.key, sum(substr(src.value,5)) FROM src GROUP BY src.key LIMIT 10 +POSTHOOK: query: SELECT src.key, sum(substr(src.value,5)) FROM src GROUP BY src.key ORDER BY src.key LIMIT 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/llap/ptfgroupbyjoin.q.out ql/src/test/results/clientpositive/llap/ptfgroupbyjoin.q.out new file mode 100644 index 0000000000..191f75ab8b --- /dev/null +++ ql/src/test/results/clientpositive/llap/ptfgroupbyjoin.q.out @@ -0,0 +1,531 @@ +PREHOOK: query: create table tlb1 (id int, fkey int, val string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tlb1 +POSTHOOK: query: create table tlb1 (id int, fkey int, val string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tlb1 +PREHOOK: query: create table tlb2 (fid int, name string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tlb2 +POSTHOOK: query: create table tlb2 (fid int, name string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tlb2 +PREHOOK: query: insert into table tlb1 values(100,1,'abc') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@tlb1 +POSTHOOK: query: insert into table tlb1 values(100,1,'abc') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@tlb1 +POSTHOOK: Lineage: tlb1.fkey SCRIPT [] +POSTHOOK: Lineage: tlb1.id SCRIPT [] +POSTHOOK: Lineage: tlb1.val SCRIPT [] +PREHOOK: query: insert into table tlb1 values(200,1,'efg') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@tlb1 +POSTHOOK: query: insert into table tlb1 values(200,1,'efg') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@tlb1 +POSTHOOK: Lineage: tlb1.fkey SCRIPT [] +POSTHOOK: Lineage: tlb1.id SCRIPT [] +POSTHOOK: Lineage: tlb1.val SCRIPT [] +PREHOOK: query: insert into table tlb2 values(1, 'key1') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@tlb2 +POSTHOOK: query: insert into table tlb2 values(1, 'key1') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@tlb2 +POSTHOOK: Lineage: tlb2.fid SCRIPT [] +POSTHOOK: Lineage: tlb2.name SCRIPT [] +PREHOOK: query: explain +select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +PREHOOK: type: QUERY +PREHOOK: Input: default@tlb1 +PREHOOK: Input: default@tlb2 +#### A masked pattern was here #### +POSTHOOK: query: explain +select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tlb1 +POSTHOOK: Input: default@tlb2 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tlb1 + filterExpr: fkey is not null (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: fkey is not null (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: fkey (type: int), id (type: int) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: aaa + filterExpr: fid is not null (type: boolean) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: fid is not null (type: boolean) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: fid (type: int), name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +PREHOOK: type: QUERY +PREHOOK: Input: default@tlb1 +PREHOOK: Input: default@tlb2 +#### A masked pattern was here #### +POSTHOOK: query: select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tlb1 +POSTHOOK: Input: default@tlb2 +#### A masked pattern was here #### +100 1 key1 +200 1 key1 +PREHOOK: query: explain +select ddd.id, ddd.fkey, aaa.name, ddd.rnum +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +PREHOOK: type: QUERY +PREHOOK: Input: default@tlb1 +PREHOOK: Input: default@tlb2 +#### A masked pattern was here #### +POSTHOOK: query: explain +select ddd.id, ddd.fkey, aaa.name, ddd.rnum +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tlb1 +POSTHOOK: Input: default@tlb2 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tlb1 + filterExpr: fkey is not null (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: fkey is not null (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: id (type: int), fkey (type: int) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: aaa + filterExpr: fid is not null (type: boolean) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: fid is not null (type: boolean) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: fid (type: int), name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col1: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST + partition by: _col0, _col1 + raw input shape: + window functions: + window function definition + alias: row_number_window_0 + name: row_number + window function: GenericUDAFRowNumberEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), row_number_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col4 + Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col4 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select ddd.id, ddd.fkey, aaa.name, ddd.rnum +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +PREHOOK: type: QUERY +PREHOOK: Input: default@tlb1 +PREHOOK: Input: default@tlb2 +#### A masked pattern was here #### +POSTHOOK: query: select ddd.id, ddd.fkey, aaa.name, ddd.rnum +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tlb1 +POSTHOOK: Input: default@tlb2 +#### A masked pattern was here #### +100 1 key1 1 +200 1 key1 1 +PREHOOK: query: explain +select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +PREHOOK: type: QUERY +PREHOOK: Input: default@tlb1 +PREHOOK: Input: default@tlb2 +#### A masked pattern was here #### +POSTHOOK: query: explain +select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tlb1 +POSTHOOK: Input: default@tlb2 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tlb1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: fkey is not null (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: fkey (type: int), id (type: int) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: aaa + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: fid is not null (type: boolean) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: fid (type: int), name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: int), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +PREHOOK: type: QUERY +PREHOOK: Input: default@tlb1 +PREHOOK: Input: default@tlb2 +#### A masked pattern was here #### +POSTHOOK: query: select ddd.id, ddd.fkey, aaa.name +from ( + select id, fkey, + row_number() over (partition by id, fkey) as rnum + from tlb1 group by id, fkey + ) ddd +inner join tlb2 aaa on aaa.fid = ddd.fkey +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tlb1 +POSTHOOK: Input: default@tlb2 +#### A masked pattern was here #### +100 1 key1 +200 1 key1 diff --git ql/src/test/results/clientpositive/llap/push_or.q.out ql/src/test/results/clientpositive/llap/push_or.q.out new file mode 100644 index 0000000000..1ac850df8f --- /dev/null +++ ql/src/test/results/clientpositive/llap/push_or.q.out @@ -0,0 +1,263 @@ +PREHOOK: query: drop table push_or +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table push_or +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table push_or (key int, value string) partitioned by (ds string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@push_or +POSTHOOK: query: create table push_or (key int, value string) partitioned by (ds string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@push_or +PREHOOK: query: insert overwrite table push_or partition (ds='2000-04-08') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@push_or@ds=2000-04-08 +POSTHOOK: query: insert overwrite table push_or partition (ds='2000-04-08') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@push_or@ds=2000-04-08 +POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table push_or partition (ds='2000-04-09') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@push_or@ds=2000-04-09 +POSTHOOK: query: insert overwrite table push_or partition (ds='2000-04-09') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@push_or@ds=2000-04-09 +POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain extended select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@push_or +PREHOOK: Input: default@push_or@ds=2000-04-08 +PREHOOK: Input: default@push_or@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: explain extended select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@push_or +POSTHOOK: Input: default@push_or@ds=2000-04-08 +POSTHOOK: Input: default@push_or@ds=2000-04-09 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value`, `ds` +FROM `default`.`push_or` +WHERE `key` = 5 OR `ds` = '2000-04-09' +ORDER BY `key`, `ds` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: push_or + filterExpr: ((key = 5) or (ds = '2000-04-09')) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = 5) or (ds = '2000-04-09')) (type: boolean) + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col2 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: string) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-08 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.push_or + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct push_or { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.push_or + partition_columns ds + partition_columns.types string + serialization.ddl struct push_or { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.push_or + name: default.push_or +#### A masked pattern was here #### + Partition + base file name: ds=2000-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2000-04-09 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.push_or + numFiles 1 + numRows 20 + partition_columns ds + partition_columns.types string + rawDataSize 160 + serialization.ddl struct push_or { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.push_or + partition_columns ds + partition_columns.types string + serialization.ddl struct push_or { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.push_or + name: default.push_or + Truncated Path -> Alias: + /push_or/ds=2000-04-08 [push_or] + /push_or/ds=2000-04-09 [push_or] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types int:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds +PREHOOK: type: QUERY +PREHOOK: Input: default@push_or +PREHOOK: Input: default@push_or@ds=2000-04-08 +PREHOOK: Input: default@push_or@ds=2000-04-09 +#### A masked pattern was here #### +POSTHOOK: query: select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds +POSTHOOK: type: QUERY +POSTHOOK: Input: default@push_or +POSTHOOK: Input: default@push_or@ds=2000-04-08 +POSTHOOK: Input: default@push_or@ds=2000-04-09 +#### A masked pattern was here #### +0 val_0 2000-04-09 +0 val_0 2000-04-09 +0 val_0 2000-04-09 +2 val_2 2000-04-09 +4 val_4 2000-04-09 +5 val_5 2000-04-08 +5 val_5 2000-04-08 +5 val_5 2000-04-08 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +5 val_5 2000-04-09 +8 val_8 2000-04-09 +9 val_9 2000-04-09 +10 val_10 2000-04-09 +11 val_11 2000-04-09 +12 val_12 2000-04-09 +12 val_12 2000-04-09 +15 val_15 2000-04-09 +15 val_15 2000-04-09 +17 val_17 2000-04-09 +18 val_18 2000-04-09 +18 val_18 2000-04-09 +19 val_19 2000-04-09 diff --git ql/src/test/results/clientpositive/llap/query_result_fileformat.q.out ql/src/test/results/clientpositive/llap/query_result_fileformat.q.out new file mode 100644 index 0000000000..9ec2364f97 --- /dev/null +++ ql/src/test/results/clientpositive/llap/query_result_fileformat.q.out @@ -0,0 +1,148 @@ +PREHOOK: query: create table nzhang_test1 stored as sequencefile as select 'key1' as key, 'value +1 + +http://asdf' value from src limit 1 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@nzhang_test1 +POSTHOOK: query: create table nzhang_test1 stored as sequencefile as select 'key1' as key, 'value +1 + +http://asdf' value from src limit 1 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nzhang_test1 +POSTHOOK: Lineage: nzhang_test1.key SIMPLE [] +POSTHOOK: Lineage: nzhang_test1.value SIMPLE [] +PREHOOK: query: select * from nzhang_test1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: select * from nzhang_test1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +key1 value +1 + +http://asdf +PREHOOK: query: select count(*) from nzhang_test1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from nzhang_test1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +1 +PREHOOK: query: explain vectorization detail +select * from nzhang_test1 where key='key1' +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization detail +select * from nzhang_test1 where key='key1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: nzhang_test1 + filterExpr: (key = 'key1') (type: boolean) + Filter Operator + predicate: (key = 'key1') (type: boolean) + Select Operator + expressions: 'key1' (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: select * from nzhang_test1 where key='key1' +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: select * from nzhang_test1 where key='key1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +key1 value +1 + +http://asdf +PREHOOK: query: select * from nzhang_test1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: select * from nzhang_test1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +key1 value +1 + +http://asdf +PREHOOK: query: select count(*) from nzhang_test1 +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from nzhang_test1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +1 +PREHOOK: query: explain vectorization detail +select * from nzhang_test1 where key='key1' +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: explain vectorization detail +select * from nzhang_test1 where key='key1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: nzhang_test1 + filterExpr: (key = 'key1') (type: boolean) + Filter Operator + predicate: (key = 'key1') (type: boolean) + Select Operator + expressions: 'key1' (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: select * from nzhang_test1 where key='key1' +PREHOOK: type: QUERY +PREHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +POSTHOOK: query: select * from nzhang_test1 where key='key1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@nzhang_test1 +#### A masked pattern was here #### +key1 value +1 + +http://asdf diff --git ql/src/test/results/clientpositive/quote1.q.out ql/src/test/results/clientpositive/llap/quote1.q.out similarity index 55% rename from ql/src/test/results/clientpositive/quote1.q.out rename to ql/src/test/results/clientpositive/llap/quote1.q.out index cfae5b4cd5..c3867ffa34 100644 --- ql/src/test/results/clientpositive/quote1.q.out +++ ql/src/test/results/clientpositive/llap/quote1.q.out @@ -20,82 +20,82 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1_n103@table=2008-04-08 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((UDFToDouble(key) >= 200.0D) and (UDFToDouble(key) < 300.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) >= 200.0D) and (UDFToDouble(key) < 300.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(key) (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n103 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((UDFToDouble(key) >= 200.0D) and (UDFToDouble(key) < 300.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(key) >= 200.0D) and (UDFToDouble(key) < 300.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5225 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n103 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '2008-04-08' (type: string) + outputColumnNames: location, type, table + Statistics: Num rows: 55 Data size: 10395 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(location, 'hll'), compute_stats(type, 'hll') + keys: table (type: string) + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct), _col2 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2008-04-08' (type: string) - outputColumnNames: location, type, table - Statistics: Num rows: 55 Data size: 10395 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(location, 'hll'), compute_stats(type, 'hll') - keys: table (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: struct), _col2 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -109,7 +109,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1_n103 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -117,36 +117,6 @@ STAGE PLANS: Column Types: int, string Table: default.dest1_n103 - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n103 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n103 - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - PREHOOK: query: EXPLAIN SELECT `int`.`location`, `int`.`type`, `int`.`table` FROM dest1_n103 `int` WHERE `int`.`table` = '2008-04-08' PREHOOK: type: QUERY @@ -168,14 +138,11 @@ STAGE PLANS: TableScan alias: int filterExpr: (table = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (table = '2008-04-08') (type: boolean) - Statistics: Num rows: 1 Data size: 268 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: location (type: int), type (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: FROM src diff --git ql/src/test/results/clientpositive/quote2.q.out ql/src/test/results/clientpositive/llap/quote2.q.out similarity index 91% rename from ql/src/test/results/clientpositive/quote2.q.out rename to ql/src/test/results/clientpositive/llap/quote2.q.out index 8d350da36e..16ccb79acb 100644 --- ql/src/test/results/clientpositive/quote2.q.out +++ ql/src/test/results/clientpositive/llap/quote2.q.out @@ -44,14 +44,11 @@ STAGE PLANS: Processor Tree: TableScan alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: 'abc' (type: string), 'abc' (type: string), 'abc'' (type: string), 'abc"' (type: string), 'abc\' (type: string), 'abc\' (type: string), 'abc\'' (type: string), 'abc\"' (type: string), 'abc\\' (type: string), 'abc\\' (type: string), 'abc\\'' (type: string), 'abc\\"' (type: string), 'abc\\\' (type: string), 'abc\\\' (type: string), 'abc""""\' (type: string), 'abc''''\' (type: string), 'mysql_%\_\%' (type: string), 'mysql\\_\\\%' (type: string), 'awk '{print NR"\t"$0}'' (type: string), 'tab tab' (type: string), 'tab tab' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 500 Data size: 952500 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 - Statistics: Num rows: 1 Data size: 1905 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT diff --git ql/src/test/results/clientpositive/llap/quotedid_basic.q.out ql/src/test/results/clientpositive/llap/quotedid_basic.q.out new file mode 100644 index 0000000000..15b1219ce6 --- /dev/null +++ ql/src/test/results/clientpositive/llap/quotedid_basic.q.out @@ -0,0 +1,510 @@ +PREHOOK: query: create table t1_n7(`x+1` string, `y&y` string, `!@#$%^&*()_q` string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t1_n7 +POSTHOOK: query: create table t1_n7(`x+1` string, `y&y` string, `!@#$%^&*()_q` string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1_n7 +PREHOOK: query: describe t1_n7 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@t1_n7 +POSTHOOK: query: describe t1_n7 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@t1_n7 +x+1 string +y&y string +!@#$%^&*()_q string +PREHOOK: query: select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +POSTHOOK: query: select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: t1_n7 + Select Operator + expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: t1_n7 + filterExpr: (!@#$%^&*()_q = '1') (type: boolean) + Filter Operator + predicate: (!@#$%^&*()_q = '1') (type: boolean) + Select Operator + expressions: x+1 (type: string), y&y (type: string), '1' (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n7 + filterExpr: (!@#$%^&*()_q = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (!@#$%^&*()_q = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: x+1 (type: string), y&y (type: string) + outputColumnNames: x+1, y&y + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: x+1 (type: string), y&y (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) +from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) +from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n7 + filterExpr: (!@#$%^&*()_q = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (!@#$%^&*()_q = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: x+1 (type: string), y&y (type: string) + outputColumnNames: x+1, y&y + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: x+1 (type: string), y&y (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: '1' (type: string), _col1 (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: '1' (type: string) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS LAST + partition by: '1' + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col1 + name: rank + window function: GenericUDAFRankEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '1' (type: string), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select `X+1`, `Y&y`, `!@#$%^&*()_Q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) +from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&Y`, `!@#$%^&*()_q` having `!@#$%^&*()_Q` = '1' +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +POSTHOOK: query: explain select `X+1`, `Y&y`, `!@#$%^&*()_Q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) +from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&Y`, `!@#$%^&*()_q` having `!@#$%^&*()_Q` = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n7 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n7 + filterExpr: (!@#$%^&*()_q = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (!@#$%^&*()_q = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: x+1 (type: string), y&y (type: string) + outputColumnNames: x+1, y&y + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: x+1 (type: string), y&y (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: '1' (type: string), _col1 (type: string) + null sort order: az + sort order: ++ + Map-reduce partition columns: '1' (type: string) + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 ASC NULLS LAST + partition by: '1' + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col1 + name: rank + window function: GenericUDAFRankEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '1' (type: string), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: create table `t4```(`x+1``` string, `y&y` string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t4` +POSTHOOK: query: create table `t4```(`x+1``` string, `y&y` string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t4` +PREHOOK: query: describe `t4``` +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@t4` +POSTHOOK: query: describe `t4``` +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@t4` +x+1` string +y&y string +PREHOOK: query: insert into table `t4``` select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@t4` +POSTHOOK: query: insert into table `t4``` select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@t4` +POSTHOOK: Lineage: t4`.x+1` SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: t4`.y&y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) +from `t4``` where `x+1``` = '10' group by `x+1```, `y&y` having `x+1``` = '10' +PREHOOK: type: QUERY +PREHOOK: Input: default@t4` +#### A masked pattern was here #### +POSTHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) +from `t4``` where `x+1``` = '10' group by `x+1```, `y&y` having `x+1``` = '10' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t4` +#### A masked pattern was here #### +10 val_10 1 +PREHOOK: query: create view v1 as +select `x+1```, `y&y` +from `t4``` where `x+1``` < '200' +PREHOOK: type: CREATEVIEW +PREHOOK: Input: default@t4` +PREHOOK: Output: database:default +PREHOOK: Output: default@v1 +POSTHOOK: query: create view v1 as +select `x+1```, `y&y` +from `t4``` where `x+1``` < '200' +POSTHOOK: type: CREATEVIEW +POSTHOOK: Input: default@t4` +POSTHOOK: Output: database:default +POSTHOOK: Output: default@v1 +POSTHOOK: Lineage: v1.x+1` SIMPLE [(t4`)t4`.FieldSchema(name:x+1`, type:string, comment:null), ] +POSTHOOK: Lineage: v1.y&y SIMPLE [(t4`)t4`.FieldSchema(name:y&y, type:string, comment:null), ] +PREHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) +from v1 +group by `x+1```, `y&y` +PREHOOK: type: QUERY +PREHOOK: Input: default@t4` +PREHOOK: Input: default@v1 +#### A masked pattern was here #### +POSTHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) +from v1 +group by `x+1```, `y&y` +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t4` +POSTHOOK: Input: default@v1 +#### A masked pattern was here #### +0 val_0 1 +10 val_10 1 +100 val_100 1 +103 val_103 1 +104 val_104 1 +105 val_105 1 +11 val_11 1 +111 val_111 1 +113 val_113 1 +114 val_114 1 +116 val_116 1 +118 val_118 1 +119 val_119 1 +12 val_12 1 +120 val_120 1 +125 val_125 1 +126 val_126 1 +128 val_128 1 +129 val_129 1 +131 val_131 1 +133 val_133 1 +134 val_134 1 +136 val_136 1 +137 val_137 1 +138 val_138 1 +143 val_143 1 +145 val_145 1 +146 val_146 1 +149 val_149 1 +15 val_15 1 +150 val_150 1 +152 val_152 1 +153 val_153 1 +155 val_155 1 +156 val_156 1 +157 val_157 1 +158 val_158 1 +160 val_160 1 +162 val_162 1 +163 val_163 1 +164 val_164 1 +165 val_165 1 +166 val_166 1 +167 val_167 1 +168 val_168 1 +169 val_169 1 +17 val_17 1 +170 val_170 1 +172 val_172 1 +174 val_174 1 +175 val_175 1 +176 val_176 1 +177 val_177 1 +178 val_178 1 +179 val_179 1 +18 val_18 1 +180 val_180 1 +181 val_181 1 +183 val_183 1 +186 val_186 1 +187 val_187 1 +189 val_189 1 +19 val_19 1 +190 val_190 1 +191 val_191 1 +192 val_192 1 +193 val_193 1 +194 val_194 1 +195 val_195 1 +196 val_196 1 +197 val_197 1 +199 val_199 1 +2 val_2 1 +20 val_20 1 diff --git ql/src/test/results/clientpositive/quotedid_partition.q.out ql/src/test/results/clientpositive/llap/quotedid_partition.q.out similarity index 87% rename from ql/src/test/results/clientpositive/quotedid_partition.q.out rename to ql/src/test/results/clientpositive/llap/quotedid_partition.q.out index 4ef64c375c..a5434d3de9 100644 --- ql/src/test/results/clientpositive/quotedid_partition.q.out +++ ql/src/test/results/clientpositive/llap/quotedid_partition.q.out @@ -43,49 +43,58 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src_p - filterExpr: ((x+1 = '10') and (!@#$%^&*()_q = 'a')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (x+1 = '10') (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: y&y (type: string) - outputColumnNames: y&y - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: y&y (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: '10' (type: string), _col0 (type: string), 'a' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src_p + filterExpr: ((x+1 = '10') and (!@#$%^&*()_q = 'a')) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (x+1 = '10') (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: y&y (type: string) + outputColumnNames: y&y + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: y&y (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: '10' (type: string), _col0 (type: string), 'a' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/quotedid_skew.q.out ql/src/test/results/clientpositive/llap/quotedid_skew.q.out new file mode 100644 index 0000000000..40bcc0fd35 --- /dev/null +++ ql/src/test/results/clientpositive/llap/quotedid_skew.q.out @@ -0,0 +1,129 @@ +PREHOOK: query: CREATE TABLE T1_n46(`!@#$%^&*()_q` string, `y&y` string) +SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n46 +POSTHOOK: query: CREATE TABLE T1_n46(`!@#$%^&*()_q` string, `y&y` string) +SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n46 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n46 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n46 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n46 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n46 +PREHOOK: query: CREATE TABLE T2_n28(`!@#$%^&*()_q` string, `y&y` string) +SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n28 +POSTHOOK: query: CREATE TABLE T2_n28(`!@#$%^&*()_q` string, `y&y` string) +SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n28 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T2_n28 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n28 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T2_n28 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n28 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n46 a JOIN T2_n28 b ON a. `!@#$%^&*()_q` = b. `!@#$%^&*()_q` +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n46 +PREHOOK: Input: default@t2_n28 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n46 a JOIN T2_n28 b ON a. `!@#$%^&*()_q` = b. `!@#$%^&*()_q` +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n46 +POSTHOOK: Input: default@t2_n28 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: !@#$%^&*()_q is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: !@#$%^&*()_q is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: !@#$%^&*()_q (type: string), y&y (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: !@#$%^&*()_q is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: !@#$%^&*()_q is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: !@#$%^&*()_q (type: string), y&y (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/rand_partitionpruner1.q.out ql/src/test/results/clientpositive/llap/rand_partitionpruner1.q.out new file mode 100644 index 0000000000..d2d6e58a9f --- /dev/null +++ ql/src/test/results/clientpositive/llap/rand_partitionpruner1.q.out @@ -0,0 +1,94 @@ +PREHOOK: query: explain extended select * from src where rand(1) < 0.1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain extended select * from src where rand(1) < 0.1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT `key`, `value` +FROM `default`.`src` +WHERE RAND(1) < 0.1 +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (rand(1) < 0.1D) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: select * from src where rand(1) < 0.1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * from src where rand(1) < 0.1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +409 val_409 +429 val_429 +209 val_209 +153 val_153 +203 val_203 +170 val_170 +489 val_489 +378 val_378 +221 val_221 +498 val_498 +469 val_469 +176 val_176 +176 val_176 +384 val_384 +217 val_217 +431 val_431 +51 val_51 +288 val_288 +457 val_457 +197 val_197 +77 val_77 +138 val_138 +277 val_277 +224 val_224 +309 val_309 +389 val_389 +331 val_331 +317 val_317 +336 val_336 +42 val_42 +458 val_458 +78 val_78 +453 val_453 +74 val_74 +103 val_103 +467 val_467 +202 val_202 +469 val_469 +44 val_44 +454 val_454 +70 val_70 +491 val_491 +199 val_199 +169 val_169 +310 val_310 +233 val_233 +133 val_133 +26 val_26 +134 val_134 +18 val_18 +298 val_298 +348 val_348 +469 val_469 +37 val_37 +152 val_152 +400 val_400 diff --git ql/src/test/results/clientpositive/llap/rand_partitionpruner2.q.out ql/src/test/results/clientpositive/llap/rand_partitionpruner2.q.out new file mode 100644 index 0000000000..ef5509281a --- /dev/null +++ ql/src/test/results/clientpositive/llap/rand_partitionpruner2.q.out @@ -0,0 +1,432 @@ +PREHOOK: query: create table tmptable_n1(key string, value string, hr string, ds string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmptable_n1 +POSTHOOK: query: create table tmptable_n1(key string, value string, hr string, ds string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmptable_n1 +PREHOOK: query: explain extended +insert overwrite table tmptable_n1 +select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@tmptable_n1 +POSTHOOK: query: explain extended +insert overwrite table tmptable_n1 +select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@tmptable_n1 +OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` +FROM `default`.`srcpart` +WHERE RAND(1) < 0.1 AND `ds` = '2008-04-08' +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (rand(1) < 0.1D) (type: boolean) + Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value,hr,ds + columns.comments + columns.types string:string:string:string +#### A masked pattern was here #### + name default.tmptable_n1 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable_n1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, hr, ds + Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(hr, 'hll'), compute_stats(ds, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types struct:struct:struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value,hr,ds + columns.comments + columns.types string:string:string:string +#### A masked pattern was here #### + name default.tmptable_n1 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable_n1 + + Stage: Stage-3 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value, hr, ds + Column Types: string, string, string, string + Table: default.tmptable_n1 + Is Table Level Stats: true + +PREHOOK: query: insert overwrite table tmptable_n1 +select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@tmptable_n1 +POSTHOOK: query: insert overwrite table tmptable_n1 +select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@tmptable_n1 +POSTHOOK: Lineage: tmptable_n1.ds SIMPLE [(srcpart)a.FieldSchema(name:hr, type:string, comment:null), ] +POSTHOOK: Lineage: tmptable_n1.hr SIMPLE [] +POSTHOOK: Lineage: tmptable_n1.key SIMPLE [(srcpart)a.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable_n1.value SIMPLE [(srcpart)a.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from tmptable_n1 x sort by x.key,x.value,x.ds,x.hr +PREHOOK: type: QUERY +PREHOOK: Input: default@tmptable_n1 +#### A masked pattern was here #### +POSTHOOK: query: select * from tmptable_n1 x sort by x.key,x.value,x.ds,x.hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tmptable_n1 +#### A masked pattern was here #### +103 val_103 2008-04-08 11 +118 val_118 2008-04-08 12 +119 val_119 2008-04-08 12 +119 val_119 2008-04-08 12 +126 val_126 2008-04-08 12 +131 val_131 2008-04-08 12 +133 val_133 2008-04-08 11 +134 val_134 2008-04-08 11 +138 val_138 2008-04-08 11 +143 val_143 2008-04-08 12 +152 val_152 2008-04-08 11 +153 val_153 2008-04-08 11 +162 val_162 2008-04-08 12 +169 val_169 2008-04-08 11 +170 val_170 2008-04-08 11 +175 val_175 2008-04-08 12 +176 val_176 2008-04-08 11 +176 val_176 2008-04-08 11 +18 val_18 2008-04-08 11 +18 val_18 2008-04-08 12 +191 val_191 2008-04-08 12 +197 val_197 2008-04-08 11 +199 val_199 2008-04-08 11 +200 val_200 2008-04-08 12 +201 val_201 2008-04-08 12 +202 val_202 2008-04-08 11 +203 val_203 2008-04-08 11 +209 val_209 2008-04-08 11 +214 val_214 2008-04-08 12 +217 val_217 2008-04-08 11 +218 val_218 2008-04-08 12 +221 val_221 2008-04-08 11 +223 val_223 2008-04-08 12 +224 val_224 2008-04-08 11 +229 val_229 2008-04-08 12 +230 val_230 2008-04-08 12 +233 val_233 2008-04-08 11 +233 val_233 2008-04-08 12 +237 val_237 2008-04-08 12 +238 val_238 2008-04-08 12 +256 val_256 2008-04-08 12 +26 val_26 2008-04-08 11 +265 val_265 2008-04-08 12 +273 val_273 2008-04-08 12 +277 val_277 2008-04-08 11 +277 val_277 2008-04-08 12 +280 val_280 2008-04-08 12 +286 val_286 2008-04-08 12 +288 val_288 2008-04-08 11 +298 val_298 2008-04-08 11 +309 val_309 2008-04-08 11 +309 val_309 2008-04-08 12 +310 val_310 2008-04-08 11 +317 val_317 2008-04-08 11 +322 val_322 2008-04-08 12 +323 val_323 2008-04-08 12 +325 val_325 2008-04-08 12 +331 val_331 2008-04-08 11 +332 val_332 2008-04-08 12 +336 val_336 2008-04-08 11 +336 val_336 2008-04-08 12 +339 val_339 2008-04-08 12 +341 val_341 2008-04-08 12 +342 val_342 2008-04-08 12 +348 val_348 2008-04-08 11 +348 val_348 2008-04-08 12 +35 val_35 2008-04-08 12 +364 val_364 2008-04-08 12 +37 val_37 2008-04-08 11 +378 val_378 2008-04-08 11 +384 val_384 2008-04-08 11 +389 val_389 2008-04-08 11 +400 val_400 2008-04-08 11 +403 val_403 2008-04-08 12 +407 val_407 2008-04-08 12 +409 val_409 2008-04-08 11 +417 val_417 2008-04-08 12 +42 val_42 2008-04-08 11 +424 val_424 2008-04-08 12 +429 val_429 2008-04-08 11 +429 val_429 2008-04-08 12 +430 val_430 2008-04-08 12 +431 val_431 2008-04-08 11 +432 val_432 2008-04-08 12 +44 val_44 2008-04-08 11 +453 val_453 2008-04-08 11 +454 val_454 2008-04-08 11 +457 val_457 2008-04-08 11 +457 val_457 2008-04-08 12 +458 val_458 2008-04-08 11 +466 val_466 2008-04-08 12 +467 val_467 2008-04-08 11 +469 val_469 2008-04-08 11 +469 val_469 2008-04-08 11 +469 val_469 2008-04-08 11 +47 val_47 2008-04-08 12 +470 val_470 2008-04-08 12 +489 val_489 2008-04-08 11 +491 val_491 2008-04-08 11 +496 val_496 2008-04-08 12 +498 val_498 2008-04-08 11 +498 val_498 2008-04-08 12 +51 val_51 2008-04-08 11 +58 val_58 2008-04-08 12 +70 val_70 2008-04-08 11 +72 val_72 2008-04-08 12 +74 val_74 2008-04-08 11 +77 val_77 2008-04-08 11 +77 val_77 2008-04-08 12 +78 val_78 2008-04-08 11 +82 val_82 2008-04-08 12 +87 val_87 2008-04-08 12 +90 val_90 2008-04-08 12 +97 val_97 2008-04-08 12 +97 val_97 2008-04-08 12 +98 val_98 2008-04-08 12 diff --git ql/src/test/results/clientpositive/rand_partitionpruner3.q.out ql/src/test/results/clientpositive/llap/rand_partitionpruner3.q.out similarity index 61% rename from ql/src/test/results/clientpositive/rand_partitionpruner3.q.out rename to ql/src/test/results/clientpositive/llap/rand_partitionpruner3.q.out index 0225e57dc1..b7f387c05c 100644 --- ql/src/test/results/clientpositive/rand_partitionpruner3.q.out +++ ql/src/test/results/clientpositive/llap/rand_partitionpruner3.q.out @@ -12,56 +12,14 @@ OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` FROM `default`.`srcpart` WHERE CAST(`key` AS DOUBLE) BETWEEN 10 AND 50 AND RAND(1) < 0.1 AND `ds` = '2008-04-08' AND `hr` LIKE '%2' STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (UDFToDouble(key) BETWEEN 10.0D AND 50.0D and (rand(1) < 0.1D)) (type: boolean) - Statistics: Num rows: 18 Data size: 6516 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 18 Data size: 8208 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 18 Data size: 8208 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -108,14 +66,17 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=12 [a] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: a + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (UDFToDouble(key) BETWEEN 10.0D AND 50.0D and (rand(1) < 0.1D)) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' and not(key > 50 or key < 10) and a.hr like '%2' PREHOOK: type: QUERY @@ -143,57 +104,14 @@ OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` FROM `default`.`srcpart` WHERE CAST(`key` AS DOUBLE) BETWEEN 10 AND 50 AND `ds` = '2008-04-08' AND `hr` LIKE '%2' STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: (UDFToDouble(key) BETWEEN 10.0D AND 50.0D and (ds = '2008-04-08') and (hr like '%2')) (type: boolean) - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: UDFToDouble(key) BETWEEN 10.0D AND 50.0D (type: boolean) - Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 25080 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 25080 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: Partition - base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -240,14 +158,18 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=12 [a] - - Stage: Stage-0 - Fetch Operator - limit: -1 Processor Tree: - ListSink + TableScan + alias: a + filterExpr: (UDFToDouble(key) BETWEEN 10.0D AND 50.0D and (ds = '2008-04-08') and (hr like '%2')) (type: boolean) + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: UDFToDouble(key) BETWEEN 10.0D AND 50.0D (type: boolean) + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: select a.* from srcpart a where a.ds = '2008-04-08' and not(key > 50 or key < 10) and a.hr like '%2' PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/rcfile_null_value.q.out ql/src/test/results/clientpositive/llap/rcfile_null_value.q.out new file mode 100644 index 0000000000..52506bfb8c --- /dev/null +++ ql/src/test/results/clientpositive/llap/rcfile_null_value.q.out @@ -0,0 +1,280 @@ +PREHOOK: query: CREATE TABLE src1_rc(key STRING, value STRING) STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src1_rc +POSTHOOK: query: CREATE TABLE src1_rc(key STRING, value STRING) STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src1_rc +PREHOOK: query: INSERT OVERWRITE TABLE src1_rc SELECT * FROM src1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src1 +PREHOOK: Output: default@src1_rc +POSTHOOK: query: INSERT OVERWRITE TABLE src1_rc SELECT * FROM src1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1 +POSTHOOK: Output: default@src1_rc +POSTHOOK: Lineage: src1_rc.key SIMPLE [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src1_rc.value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: SELECT * FROM src1_rc +PREHOOK: type: QUERY +PREHOOK: Input: default@src1_rc +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM src1_rc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src1_rc +#### A masked pattern was here #### +238 val_238 + +311 val_311 + val_27 + val_165 + val_409 +255 val_255 +278 val_278 +98 val_98 + val_484 + val_265 + val_193 +401 val_401 +150 val_150 +273 val_273 +224 +369 +66 val_66 +128 +213 val_213 +146 val_146 +406 val_406 + + + +PREHOOK: query: CREATE TABLE dest1_rc(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest1_rc +POSTHOOK: query: CREATE TABLE dest1_rc(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest1_rc +PREHOOK: query: EXPLAIN +FROM ( + FROM + ( + FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 + ) a + RIGHT OUTER JOIN + ( + FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 + ) b + ON (a.c1 = b.c3) + SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 +) c +INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest1_rc +POSTHOOK: query: EXPLAIN +FROM ( + FROM + ( + FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 + ) a + RIGHT OUTER JOIN + ( + FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 + ) b + ON (a.c1 = b.c3) + SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 +) c +INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest1_rc +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src2 + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.dest1_rc + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: c1, c2, c3, c4 + Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') + minReductionHashAggr: 0.9818182 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.dest1_rc + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: c1, c2, c3, c4 + Column Types: int, string, int, string + Table: default.dest1_rc + +PREHOOK: query: FROM ( + FROM + ( + FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 + ) a + RIGHT OUTER JOIN + ( + FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 + ) b + ON (a.c1 = b.c3) + SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 +) c +INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@dest1_rc +POSTHOOK: query: FROM ( + FROM + ( + FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 + ) a + RIGHT OUTER JOIN + ( + FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 + ) b + ON (a.c1 = b.c3) + SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 +) c +INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@dest1_rc +POSTHOOK: Lineage: dest1_rc.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_rc.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_rc.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: dest1_rc.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: SELECT dest1_rc.* FROM dest1_rc +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1_rc +#### A masked pattern was here #### +POSTHOOK: query: SELECT dest1_rc.* FROM dest1_rc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1_rc +#### A masked pattern was here #### +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +NULL NULL 20 val_20 +NULL NULL 24 val_24 +NULL NULL 24 val_24 diff --git ql/src/test/results/clientpositive/reduceSinkDeDuplication_pRS_key_empty.q.out ql/src/test/results/clientpositive/llap/reduceSinkDeDuplication_pRS_key_empty.q.out similarity index 54% rename from ql/src/test/results/clientpositive/reduceSinkDeDuplication_pRS_key_empty.q.out rename to ql/src/test/results/clientpositive/llap/reduceSinkDeDuplication_pRS_key_empty.q.out index 298b104a9f..610358f4da 100644 --- ql/src/test/results/clientpositive/reduceSinkDeDuplication_pRS_key_empty.q.out +++ ql/src/test/results/clientpositive/llap/reduceSinkDeDuplication_pRS_key_empty.q.out @@ -22,7 +22,7 @@ select POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -{"columntype":"Double","min":260.182,"max":260.182,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":FM} {"columntype":"String","maxlength":2,"avglength":2.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":FM@} {"columntype":"Double","min":20428.07287599998,"max":20428.07287599998,"countnulls":0,"numdistinctvalues":2,"ndvbitvector":FM} {"columntype":"Double","min":20469.01089779557,"max":20469.01089779557,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":FM } +{"columntype":"Double","min":260.182,"max":260.182,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":FM} {"columntype":"String","maxlength":2,"avglength":2.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":FM@} {"columntype":"Double","min":20428.072876000006,"max":20428.072876000006,"countnulls":0,"numdistinctvalues":2,"ndvbitvector":FM@} {"columntype":"Double","min":20469.010897795597,"max":20469.010897795597,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":FM�} PREHOOK: query: explain select compute_stats(a,'fm',16),compute_stats(b,'fm',16),compute_stats(c,'fm',16),compute_stats(d,'fm',16) from ( @@ -53,39 +53,48 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: substr(value, 5) (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) - mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(_col0, 'fm', 16), compute_stats(_col1, 'fm', 16), compute_stats(_col2, 'fm', 16), compute_stats(_col3, 'fm', 16) - mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: substr(value, 5) (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(_col0, 'fm', 16), compute_stats(_col1, 'fm', 16), compute_stats(_col2, 'fm', 16), compute_stats(_col3, 'fm', 16) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -144,62 +153,61 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: substr(value, 5) (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) - mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double), _col1 (type: string), _col2 (type: double), _col3 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0, 'fm', 16), compute_stats(VALUE._col3, 'fm', 16), compute_stats(VALUE._col4, 'fm', 16), compute_stats(VALUE._col5, 'fm', 16) - mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: substr(value, 5) (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: avg(DISTINCT KEY._col0:0._col0), max(KEY._col0:0._col0), variance(KEY._col0:0._col0), var_samp(KEY._col0:0._col0) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double), _col1 (type: string), _col2 (type: double), _col3 (type: double) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0, 'fm', 16), compute_stats(VALUE._col3, 'fm', 16), compute_stats(VALUE._col4, 'fm', 16), compute_stats(VALUE._col5, 'fm', 16) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/reduce_deduplicate_exclude_join.q.out ql/src/test/results/clientpositive/llap/reduce_deduplicate_exclude_join.q.out new file mode 100644 index 0000000000..b89a4d7473 --- /dev/null +++ ql/src/test/results/clientpositive/llap/reduce_deduplicate_exclude_join.q.out @@ -0,0 +1,94 @@ +PREHOOK: query: explain select * from (select * from src cluster by key) a join src b on a.key = b.key limit 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select * from (select * from src cluster by key) a join src b on a.key = b.key limit 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 3 + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended2.q.out ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended2.q.out new file mode 100644 index 0000000000..9f41262fa4 --- /dev/null +++ ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended2.q.out @@ -0,0 +1,955 @@ +PREHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM src f +JOIN src g ON (f.key = g.key AND f.value = g.value) +GROUP BY g.value, f.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM src f +JOIN src g ON (f.key = g.key AND f.value = g.value) +GROUP BY g.value, f.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: f + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: g + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col3 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT g.key, f.value +FROM src f +JOIN src g ON (f.key = g.key AND f.value = g.value) +GROUP BY g.key, f.value +ORDER BY f.value, g.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT g.key, f.value +FROM src f +JOIN src g ON (f.key = g.key AND f.value = g.value) +GROUP BY g.key, f.value +ORDER BY f.value, g.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: f + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: g + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string), _col0 (type: string) + 1 _col1 (type: string), _col0 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: string), _col2 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM src f +JOIN ( + SELECT key, value + FROM src + GROUP BY key, value) g +ON (f.key = g.key AND f.value = g.value) +GROUP BY g.value, f.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM src f +JOIN ( + SELECT key, value + FROM src + GROUP BY key, value) g +ON (f.key = g.key AND f.value = g.value) +GROUP BY g.value, f.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: f + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col3 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM ( + SELECT key, value + FROM src + GROUP BY value, key) f +JOIN ( + SELECT key, value + FROM src + GROUP BY key, value) g +ON (f.key = g.key AND f.value = g.value) +GROUP BY g.value, f.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM ( + SELECT key, value + FROM src + GROUP BY value, key) f +JOIN ( + SELECT key, value + FROM src + GROUP BY key, value) g +ON (f.key = g.key AND f.value = g.value) +GROUP BY g.value, f.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Dummy Store + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col3 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM ( + SELECT value + FROM src + GROUP BY value) g +JOIN ( + SELECT key + FROM src + GROUP BY key) f +GROUP BY g.value, f.key +ORDER BY f.key desc, g.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT f.key, g.value +FROM ( + SELECT value + FROM src + GROUP BY value) g +JOIN ( + SELECT key + FROM src + GROUP BY key) f +GROUP BY g.value, f.key +ORDER BY f.key desc, g.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 6 (XPROD_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: value (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: -+ + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT x.key, x.value +FROM ( + SELECT f.key, g.value + FROM ( + SELECT key, value + FROM src + GROUP BY key, value) f + JOIN ( + SELECT key, value + FROM src + GROUP BY value, key) g + ON (f.key = g.key AND f.value = g.value) + GROUP BY g.value, f.key +UNION ALL + SELECT f.key, g.value + FROM ( + SELECT key, value + FROM src + GROUP BY value, key) f + JOIN ( + SELECT key, value + FROM src + GROUP BY key, value) g + ON (f.key = g.key AND f.value = g.value) + GROUP BY f.key, g.value +) x +ORDER BY x.value desc, x.key desc +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT x.key, x.value +FROM ( + SELECT f.key, g.value + FROM ( + SELECT key, value + FROM src + GROUP BY key, value) f + JOIN ( + SELECT key, value + FROM src + GROUP BY value, key) g + ON (f.key = g.key AND f.value = g.value) + GROUP BY g.value, f.key +UNION ALL + SELECT f.key, g.value + FROM ( + SELECT key, value + FROM src + GROUP BY value, key) f + JOIN ( + SELECT key, value + FROM src + GROUP BY key, value) g + ON (f.key = g.key AND f.value = g.value) + GROUP BY f.key, g.value +) x +ORDER BY x.value desc, x.key desc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) + Reducer 6 <- Union 5 (SIMPLE_EDGE) + Reducer 7 <- Map 1 (SIMPLE_EDGE) + Reducer 8 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 5 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: value (type: string), key (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), key (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: value (type: string), key (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string), key (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: string), _col0 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: string), _col0 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + null sort order: zz + sort order: -- + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 7 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col1 (type: string), _col0 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: string), _col0 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 9 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: string) + null sort order: zz + sort order: -- + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Union 5 + Vertex: Union 5 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/regex_col.q.out ql/src/test/results/clientpositive/llap/regex_col.q.out new file mode 100644 index 0000000000..7b659fd49c --- /dev/null +++ ql/src/test/results/clientpositive/llap/regex_col.q.out @@ -0,0 +1,576 @@ +PREHOOK: query: EXPLAIN +SELECT * FROM srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink + +PREHOOK: query: EXPLAIN +SELECT `..` FROM srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT `..` FROM srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: EXPLAIN +SELECT srcpart.`..` FROM srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT srcpart.`..` FROM srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + Select Operator + expressions: ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: EXPLAIN +SELECT `..` FROM srcpart a JOIN srcpart b +ON a.key = b.key AND a.value = b.value +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT `..` FROM srcpart a JOIN srcpart b +ON a.key = b.key AND a.value = b.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: string), _col3 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: string), _col3 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col2, _col3, _col6, _col7 + Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: EXPLAIN +SELECT b.`..` FROM srcpart a JOIN srcpart b +ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 +ORDER BY ds, hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT b.`..` FROM srcpart a JOIN srcpart b +ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 +ORDER BY ds, hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (UDFToDouble(key) = 103.0D) (type: boolean) + Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 103.0D) (type: boolean) + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + Dynamic Partitioning Event Operator + Target column: ds (string) + Target Input: b + Partition key expr: ds + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE + Target Vertex: Map 4 + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: (UDFToDouble(key) = 103.0D) (type: boolean) + Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) = 103.0D) (type: boolean) + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) + Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string), _col2 (type: string), _col0 (type: string) + 1 _col1 (type: string), _col2 (type: string), _col0 (type: string) + outputColumnNames: _col4, _col5 + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col4 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT b.`..` FROM srcpart a JOIN srcpart b +ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 +ORDER BY ds, hr +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT b.`..` FROM srcpart a JOIN srcpart b +ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 +ORDER BY ds, hr +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +2008-04-08 11 +2008-04-08 11 +2008-04-08 11 +2008-04-08 11 +2008-04-08 12 +2008-04-08 12 +2008-04-08 12 +2008-04-08 12 +2008-04-09 11 +2008-04-09 11 +2008-04-09 11 +2008-04-09 11 +2008-04-09 12 +2008-04-09 12 +2008-04-09 12 +2008-04-09 12 +PREHOOK: query: EXPLAIN +SELECT `.e.` FROM srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT `.e.` FROM srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + ListSink + +PREHOOK: query: EXPLAIN +SELECT `d.*` FROM srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT `d.*` FROM srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + Select Operator + expressions: ds (type: string) + outputColumnNames: _col0 + ListSink + +PREHOOK: query: EXPLAIN +SELECT `(ds)?+.+` FROM srcpart +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT `(ds)?+.+` FROM srcpart +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: srcpart + Select Operator + expressions: key (type: string), value (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: EXPLAIN +SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: key (type: string), value (type: string) + null sort order: zz + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 10 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 diff --git ql/src/test/results/clientpositive/reloadJar.q.out ql/src/test/results/clientpositive/llap/reloadJar.q.out similarity index 51% rename from ql/src/test/results/clientpositive/reloadJar.q.out rename to ql/src/test/results/clientpositive/llap/reloadJar.q.out index 7d24635875..42d3d948f3 100644 --- ql/src/test/results/clientpositive/reloadJar.q.out +++ ql/src/test/results/clientpositive/llap/reloadJar.q.out @@ -17,37 +17,21 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: example_iden(key) (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: 1 Processor Tree: - ListSink + TableScan + alias: src + Select Operator + expressions: example_iden(key) (type: string) + outputColumnNames: _col0 + Limit + Number of rows: 1 + ListSink PREHOOK: query: SELECT example_iden(key) FROM src LIMIT 1 diff --git ql/src/test/results/clientpositive/remove_exprs_stats.q.out ql/src/test/results/clientpositive/llap/remove_exprs_stats.q.out similarity index 55% rename from ql/src/test/results/clientpositive/remove_exprs_stats.q.out rename to ql/src/test/results/clientpositive/llap/remove_exprs_stats.q.out index 48b88414e0..6eff55bb8b 100644 --- ql/src/test/results/clientpositive/remove_exprs_stats.q.out +++ ql/src/test/results/clientpositive/llap/remove_exprs_stats.q.out @@ -80,11 +80,9 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_n0 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid > 30 @@ -123,11 +121,9 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_n0 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid >= 30 @@ -157,38 +153,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc_n0 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: loc_orc_n0 - filterExpr: (locid < 6) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (locid < 6) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc_n0 + filterExpr: (locid < 6) (type: boolean) + Filter Operator + predicate: (locid < 6) (type: boolean) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid > 6 PREHOOK: type: QUERY @@ -226,11 +206,9 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_n0 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid >= 6 @@ -242,38 +220,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc_n0 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: loc_orc_n0 - filterExpr: (locid >= 6) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (locid >= 6) (type: boolean) - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc_n0 + filterExpr: (locid >= 6) (type: boolean) + Filter Operator + predicate: (locid >= 6) (type: boolean) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid < 1 PREHOOK: type: QUERY @@ -302,38 +264,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc_n0 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: loc_orc_n0 - filterExpr: (locid > 1) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (locid > 1) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc_n0 + filterExpr: (locid > 1) (type: boolean) + Filter Operator + predicate: (locid > 1) (type: boolean) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid <= 1 PREHOOK: type: QUERY @@ -344,38 +290,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc_n0 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: loc_orc_n0 - filterExpr: (locid <= 1) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (locid <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc_n0 + filterExpr: (locid <= 1) (type: boolean) + Filter Operator + predicate: (locid <= 1) (type: boolean) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid >= 1 PREHOOK: type: QUERY @@ -395,11 +325,9 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_n0 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid IN (-4,5,30,40) @@ -411,38 +339,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc_n0 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: loc_orc_n0 - filterExpr: (locid = 5) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (locid = 5) (type: boolean) - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: state (type: string), 5 (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc_n0 + filterExpr: (locid = 5) (type: boolean) + Filter Operator + predicate: (locid = 5) (type: boolean) + Select Operator + expressions: state (type: string), 5 (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid IN (5,2,3) PREHOOK: type: QUERY @@ -453,38 +365,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc_n0 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: loc_orc_n0 - filterExpr: (locid) IN (5, 2, 3) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (locid) IN (5, 2, 3) (type: boolean) - Statistics: Num rows: 4 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 408 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc_n0 + filterExpr: (locid) IN (5, 2, 3) (type: boolean) + Filter Operator + predicate: (locid) IN (5, 2, 3) (type: boolean) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid IN (1,6,9) PREHOOK: type: QUERY @@ -495,38 +391,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@loc_orc_n0 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: loc_orc_n0 - filterExpr: (locid) IN (1, 6) (type: boolean) - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (locid) IN (1, 6) (type: boolean) - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: loc_orc_n0 + filterExpr: (locid) IN (1, 6) (type: boolean) + Filter Operator + predicate: (locid) IN (1, 6) (type: boolean) + Select Operator + expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid IN (40,30) PREHOOK: type: QUERY @@ -591,11 +471,9 @@ STAGE PLANS: Processor Tree: TableScan alias: t_n7 - Statistics: Num rows: 2 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: s (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from loc_orc_n0 where locid is not null @@ -616,11 +494,9 @@ STAGE PLANS: Processor Tree: TableScan alias: loc_orc_n0 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: explain select * from t_n7 where s is not null @@ -687,38 +563,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n7 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t_n7 - filterExpr: s is not null (type: boolean) - Statistics: Num rows: 3 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: s is not null (type: boolean) - Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: s (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: t_n7 + filterExpr: s is not null (type: boolean) + Filter Operator + predicate: s is not null (type: boolean) + Select Operator + expressions: s (type: string) + outputColumnNames: _col0 + ListSink PREHOOK: query: explain select * from t_n7 where s is null PREHOOK: type: QUERY @@ -729,36 +589,20 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n7 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t_n7 - filterExpr: s is null (type: boolean) - Statistics: Num rows: 3 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: s is null (type: boolean) - Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: null (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: t_n7 + filterExpr: s is null (type: boolean) + Filter Operator + predicate: s is null (type: boolean) + Select Operator + expressions: null (type: string) + outputColumnNames: _col0 + ListSink diff --git ql/src/test/results/clientpositive/llap/router_join_ppr.q.out ql/src/test/results/clientpositive/llap/router_join_ppr.q.out new file mode 100644 index 0000000000..de20bb6209 --- /dev/null +++ ql/src/test/results/clientpositive/llap/router_join_ppr.q.out @@ -0,0 +1,1368 @@ +PREHOOK: query: EXPLAIN EXTENDED + FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED + FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`src` +WHERE `key` < 20 AND `key` > 15) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`srcpart` +WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key AND b.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +17 val_17 17 val_17 +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 +PREHOOK: query: EXPLAIN EXTENDED + FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key AND a.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED + FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key AND a.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`srcpart` +WHERE `key` < 20 AND `key` > 15 AND `ds` = '2008-04-08') AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`src` +WHERE `key` > 15 AND `key` < 20) AS `t2` ON `t0`.`key` = `t2`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key AND a.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key AND a.ds = '2008-04-08') + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +17 val_17 17 val_17 +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 +PREHOOK: query: EXPLAIN EXTENDED + FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED + FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`src` +WHERE `key` < 20 AND `key` > 15) AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`srcpart` +WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [b] + /srcpart/ds=2008-04-08/hr=12 [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: FROM + src a + RIGHT OUTER JOIN + srcpart b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +17 val_17 17 val_17 +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 +PREHOOK: query: EXPLAIN EXTENDED + FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED + FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +OPTIMIZED SQL: SELECT * +FROM (SELECT `key`, `value` +FROM `default`.`srcpart` +WHERE `key` < 20 AND `key` > 15 AND `ds` = '2008-04-08') AS `t0` +INNER JOIN (SELECT `key`, `value` +FROM `default`.`src` +WHERE `key` > 15 AND `key` < 20) AS `t2` ON `t0`.`key` = `t2`.`key` +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [a] + /srcpart/ds=2008-04-08/hr=12 [a] + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: string) + null sort order: z + numBuckets: -1 + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + value expressions: _col1 (type: string) + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src + name: default.src + Truncated Path -> Alias: + /src [b] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Position of Big Table: 0 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: FROM + srcpart a + RIGHT OUTER JOIN + src b + ON (a.key = b.key) + SELECT a.key, a.value, b.key, b.value + WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +17 val_17 17 val_17 +17 val_17 17 val_17 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +18 val_18 18 val_18 +19 val_19 19 val_19 +19 val_19 19 val_19 diff --git ql/src/test/results/clientpositive/llap/runtime_skewjoin_mapjoin_spark.q.out ql/src/test/results/clientpositive/llap/runtime_skewjoin_mapjoin_spark.q.out new file mode 100644 index 0000000000..b69b0377b0 --- /dev/null +++ ql/src/test/results/clientpositive/llap/runtime_skewjoin_mapjoin_spark.q.out @@ -0,0 +1,201 @@ +PREHOOK: query: CREATE TABLE T1_n94(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n94 +POSTHOOK: query: CREATE TABLE T1_n94(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n94 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n94 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n94 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n94 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n94 +PREHOOK: query: EXPLAIN +SELECT COUNT(*) FROM + (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a +JOIN + (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b +ON a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@t1_n94 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT COUNT(*) FROM + (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a +JOIN + (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b +ON a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@t1_n94 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n94 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: src2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col2 + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col0 (type: string) + Statistics: Num rows: 665 Data size: 57898 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT COUNT(*) FROM + (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a +JOIN + (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b +ON a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@t1_n94 +#### A masked pattern was here #### +POSTHOOK: query: SELECT COUNT(*) FROM + (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a +JOIN + (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b +ON a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@t1_n94 +#### A masked pattern was here #### +3 diff --git ql/src/test/results/clientpositive/sample3.q.out ql/src/test/results/clientpositive/llap/sample3.q.out similarity index 58% rename from ql/src/test/results/clientpositive/sample3.q.out rename to ql/src/test/results/clientpositive/llap/sample3.q.out index 6e709b795e..bfd0872099 100644 --- ql/src/test/results/clientpositive/sample3.q.out +++ ql/src/test/results/clientpositive/llap/sample3.q.out @@ -11,37 +11,21 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1000 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((hash(key) & 2147483647) % 5) = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: s + Filter Operator + predicate: (((hash(key) & 2147483647) % 5) = 0) (type: boolean) + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + ListSink PREHOOK: query: SELECT s.key FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s SORT BY key diff --git ql/src/test/results/clientpositive/llap/sample5.q.out ql/src/test/results/clientpositive/llap/sample5.q.out new file mode 100644 index 0000000000..d36a43679f --- /dev/null +++ ql/src/test/results/clientpositive/llap/sample5.q.out @@ -0,0 +1,476 @@ +PREHOOK: query: CREATE TABLE dest1_n69(key INT, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest1_n69 +POSTHOOK: query: CREATE TABLE dest1_n69(key INT, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest1_n69 +PREHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest1_n69 SELECT s.* + +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket +PREHOOK: Output: default@dest1_n69 +POSTHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest1_n69 SELECT s.* + +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket +POSTHOOK: Output: default@dest1_n69 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 5) = 0) (type: boolean) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.dest1_n69 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest1_n69 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n69 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket + name: default.srcbucket + Truncated Path -> Alias: + /srcbucket [s] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.dest1_n69 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest1_n69 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n69 + + Stage: Stage-3 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.dest1_n69 + Is Table Level Stats: true + +PREHOOK: query: INSERT OVERWRITE TABLE dest1_n69 SELECT s.* + +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket +PREHOOK: Output: default@dest1_n69 +POSTHOOK: query: INSERT OVERWRITE TABLE dest1_n69 SELECT s.* + +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket +POSTHOOK: Output: default@dest1_n69 +POSTHOOK: Lineage: dest1_n69.key SIMPLE [(srcbucket)s.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: dest1_n69.value SIMPLE [(srcbucket)s.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: SELECT dest1_n69.* FROM dest1_n69 SORT BY key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1_n69 +#### A masked pattern was here #### +POSTHOOK: query: SELECT dest1_n69.* FROM dest1_n69 SORT BY key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1_n69 +#### A masked pattern was here #### +1 val_2 +103 val_103 +103 val_103 +122 val_123 +122 val_123 +122 val_123 +125 val_125 +125 val_125 +125 val_126 +133 val_133 +133 val_134 +147 val_148 +147 val_148 +155 val_155 +16 val_17 +16 val_17 +161 val_162 +161 val_162 +161 val_162 +161 val_162 +162 val_162 +162 val_163 +163 val_163 +165 val_165 +165 val_165 +165 val_166 +18 val_18 +18 val_18 +194 val_194 +196 val_196 +196 val_197 +196 val_197 +196 val_197 +21 val_22 +21 val_22 +21 val_22 +21 val_22 +222 val_222 +222 val_223 +230 val_230 +230 val_230 +230 val_230 +230 val_230 +230 val_230 +237 val_237 +237 val_237 +238 val_238 +238 val_238 +238 val_239 +24 val_24 +24 val_24 +240 val_241 +246 val_247 +246 val_247 +256 val_256 +256 val_256 +256 val_257 +260 val_260 +260 val_261 +260 val_261 +264 val_265 +264 val_265 +273 val_273 +273 val_273 +273 val_273 +273 val_274 +275 val_275 +275 val_276 +275 val_276 +276 val_277 +278 val_278 +278 val_278 +278 val_279 +288 val_288 +288 val_288 +289 val_289 +289 val_290 +296 val_296 +296 val_297 +302 val_302 +302 val_303 +305 val_305 +305 val_306 +311 val_311 +311 val_311 +311 val_311 +32 val_33 +323 val_323 +323 val_324 +33 val_33 +33 val_34 +332 val_332 +335 val_335 +335 val_336 +335 val_336 +344 val_344 +344 val_344 +344 val_345 +35 val_35 +35 val_35 +35 val_35 +35 val_36 +35 val_36 +35 val_36 +352 val_353 +352 val_353 +355 val_356 +355 val_356 +362 val_362 +366 val_366 +369 val_369 +369 val_369 +369 val_369 +369 val_370 +37 val_37 +37 val_37 +373 val_373 +373 val_374 +379 val_379 +379 val_380 +391 val_392 +391 val_392 +393 val_393 +393 val_394 +393 val_394 +397 val_397 +397 val_397 +405 val_406 +407 val_407 +407 val_408 +407 val_408 +407 val_408 +41 val_41 +410 val_411 +411 val_411 +411 val_412 +416 val_417 +425 val_426 +43 val_43 +432 val_432 +432 val_433 +435 val_435 +435 val_436 +436 val_436 +436 val_437 +439 val_439 +439 val_439 +439 val_440 +439 val_440 +441 val_442 +450 val_451 +450 val_451 +453 val_453 +453 val_454 +454 val_454 +454 val_454 +454 val_454 +454 val_455 +454 val_455 +455 val_455 +455 val_456 +455 val_456 +460 val_460 +466 val_466 +466 val_466 +466 val_466 +469 val_469 +469 val_469 +469 val_469 +469 val_469 +469 val_469 +469 val_470 +470 val_470 +470 val_471 +481 val_481 +481 val_482 +484 val_484 +484 val_485 +492 val_492 +492 val_492 +492 val_493 +492 val_493 +493 val_493 +494 val_494 +494 val_495 +494 val_495 +498 val_498 +498 val_498 +498 val_498 +51 val_51 +51 val_51 +51 val_52 +52 val_53 +52 val_53 +52 val_53 +52 val_53 +53 val_53 +53 val_54 +54 val_54 +61 val_62 +68 val_69 +69 val_69 +69 val_70 +72 val_72 +72 val_72 +8 val_8 +8 val_9 +87 val_87 +87 val_88 +87 val_88 +89 val_90 +89 val_90 +89 val_90 +91 val_92 +93 val_94 +93 val_94 +93 val_94 +96 val_96 diff --git ql/src/test/results/clientpositive/sample6.q.out ql/src/test/results/clientpositive/llap/sample6.q.out similarity index 50% rename from ql/src/test/results/clientpositive/sample6.q.out rename to ql/src/test/results/clientpositive/llap/sample6.q.out index ab20f271e5..cb4756329d 100644 --- ql/src/test/results/clientpositive/sample6.q.out +++ ql/src/test/results/clientpositive/llap/sample6.q.out @@ -20,179 +20,179 @@ POSTHOOK: Input: default@srcbucket POSTHOOK: Output: default@dest1_n27 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 4) = 0) (type: boolean) - sampleDesc: BUCKET 1 OUT OF 4 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 4) = 0) (type: boolean) + sampleDesc: BUCKET 1 OUT OF 4 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.dest1_n27 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest1_n27 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n27 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket + name: default.srcbucket + Truncated Path -> Alias: + /srcbucket [s] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator bucketingVersion: 2 compressed: false - GlobalTableId: 1 + GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n27 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n27 { i32 key, string value} + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n27 TotalFiles: 1 - GatherStats: true + GatherStats: false MultiFileSpray: false - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-7 - Conditional Operator - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -223,7 +223,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest1_n27 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: #### A masked pattern was here #### @@ -233,194 +233,6 @@ STAGE PLANS: Table: default.dest1_n27 Is Table Level Stats: true - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n27 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n27 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n27 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n27 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n27 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n27 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n27 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n27 - name: default.dest1_n27 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n27 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n27 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n27 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n27 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n27 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n27 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n27 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n27 - name: default.dest1_n27 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - PREHOOK: query: INSERT OVERWRITE TABLE dest1_n27 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s PREHOOK: type: QUERY @@ -728,116 +540,125 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 4) = 3) (type: boolean) - sampleDesc: BUCKET 4 OUT OF 4 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 4) = 3) (type: boolean) + sampleDesc: BUCKET 4 OUT OF 4 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket + name: default.srcbucket + Truncated Path -> Alias: + /srcbucket [s] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1143,116 +964,125 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) + sampleDesc: BUCKET 1 OUT OF 2 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket + name: default.srcbucket + Truncated Path -> Alias: + /srcbucket [s] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -1782,115 +1612,124 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 3) = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 3) = 0) (type: boolean) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket + name: default.srcbucket + Truncated Path -> Alias: + /srcbucket [s] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -2302,115 +2141,124 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 3) = 1) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 3) = 1) (type: boolean) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket + name: default.srcbucket + Truncated Path -> Alias: + /srcbucket [s] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -2761,116 +2609,125 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) + sampleDesc: BUCKET 1 OUT OF 2 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket2 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 4 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket2 + numFiles 4 + numRows 500 + rawDataSize 5312 + serialization.ddl struct srcbucket2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 4 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket2 + numFiles 4 + numRows 500 + rawDataSize 5312 + serialization.ddl struct srcbucket2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket2 + name: default.srcbucket2 + Truncated Path -> Alias: + /srcbucket2 [s] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket2 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 4 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket2 - numFiles 4 - numRows 500 - rawDataSize 5312 - serialization.ddl struct srcbucket2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 4 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.srcbucket2 - numFiles 4 - numRows 500 - rawDataSize 5312 - serialization.ddl struct srcbucket2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket2 - name: default.srcbucket2 - Truncated Path -> Alias: - /srcbucket2 [s] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -3147,116 +3004,125 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 4) = 1) (type: boolean) - sampleDesc: BUCKET 2 OUT OF 4 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 4) = 1) (type: boolean) + sampleDesc: BUCKET 2 OUT OF 4 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket2 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 4 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket2 + numFiles 4 + numRows 500 + rawDataSize 5312 + serialization.ddl struct srcbucket2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 4 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket2 + numFiles 4 + numRows 500 + rawDataSize 5312 + serialization.ddl struct srcbucket2 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket2 + name: default.srcbucket2 + Truncated Path -> Alias: + /srcbucket2 [s] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket2 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 4 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket2 - numFiles 4 - numRows 500 - rawDataSize 5312 - serialization.ddl struct srcbucket2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 4 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.srcbucket2 - numFiles 4 - numRows 500 - rawDataSize 5312 - serialization.ddl struct srcbucket2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket2 - name: default.srcbucket2 - Truncated Path -> Alias: - /srcbucket2 [s] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -3424,116 +3290,125 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) + sampleDesc: BUCKET 1 OUT OF 2 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + bucketingVersion: 2 + key expressions: _col0 (type: int), _col1 (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + tag: -1 + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: empty_bucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.empty_bucket + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct empty_bucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.empty_bucket + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct empty_bucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.empty_bucket + name: default.empty_bucket + Truncated Path -> Alias: + /empty_bucket [s] + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: Select Operator - expressions: key (type: int), value (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator + File Output Operator bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: empty_bucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.empty_bucket - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct empty_bucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - name default.empty_bucket - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct empty_bucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.empty_bucket - name: default.empty_bucket - Truncated Path -> Alias: - /empty_bucket [s] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/sample7.q.out ql/src/test/results/clientpositive/llap/sample7.q.out new file mode 100644 index 0000000000..369a4c6ef4 --- /dev/null +++ ql/src/test/results/clientpositive/llap/sample7.q.out @@ -0,0 +1,485 @@ +PREHOOK: query: CREATE TABLE dest1_n160(key INT, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@dest1_n160 +POSTHOOK: query: CREATE TABLE dest1_n160(key INT, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@dest1_n160 +PREHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest1_n160 SELECT s.* +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s +WHERE s.key > 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket +PREHOOK: Output: default@dest1_n160 +POSTHOOK: query: EXPLAIN EXTENDED +INSERT OVERWRITE TABLE dest1_n160 SELECT s.* +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s +WHERE s.key > 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket +POSTHOOK: Output: default@dest1_n160 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + filterExpr: (key > 100) (type: boolean) + Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((((hash(key) & 2147483647) % 4) = 0) and (key > 100)) (type: boolean) + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.dest1_n160 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest1_n160 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n160 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: srcbucket + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count 2 + bucket_field_name key + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.srcbucket + numFiles 2 + numRows 1000 + rawDataSize 10603 + serialization.ddl struct srcbucket { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 11603 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcbucket + name: default.srcbucket + Truncated Path -> Alias: + /srcbucket [s] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.dest1_n160 + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct dest1_n160 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n160 + + Stage: Stage-3 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.dest1_n160 + Is Table Level Stats: true + +PREHOOK: query: INSERT OVERWRITE TABLE dest1_n160 SELECT s.* +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s +WHERE s.key > 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket +PREHOOK: Output: default@dest1_n160 +POSTHOOK: query: INSERT OVERWRITE TABLE dest1_n160 SELECT s.* +FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s +WHERE s.key > 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket +POSTHOOK: Output: default@dest1_n160 +POSTHOOK: Lineage: dest1_n160.key SIMPLE [(srcbucket)s.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: dest1_n160.value SIMPLE [(srcbucket)s.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: SELECT dest1_n160.* FROM dest1_n160 +order by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1_n160 +#### A masked pattern was here #### +POSTHOOK: query: SELECT dest1_n160.* FROM dest1_n160 +order by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1_n160 +#### A masked pattern was here #### +105 val_105 +105 val_106 +105 val_106 +110 val_111 +113 val_113 +113 val_113 +116 val_116 +116 val_117 +117 val_118 +117 val_118 +119 val_119 +119 val_119 +119 val_119 +119 val_120 +119 val_120 +119 val_120 +121 val_122 +121 val_122 +123 val_124 +123 val_124 +126 val_126 +126 val_127 +126 val_127 +134 val_134 +134 val_134 +134 val_135 +137 val_137 +137 val_137 +137 val_138 +153 val_153 +153 val_154 +153 val_154 +156 val_156 +156 val_157 +156 val_157 +157 val_157 +157 val_158 +157 val_158 +158 val_158 +163 val_163 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +177 val_177 +177 val_178 +177 val_178 +178 val_178 +178 val_179 +178 val_179 +184 val_185 +187 val_187 +187 val_187 +187 val_187 +195 val_195 +195 val_195 +197 val_197 +197 val_197 +197 val_198 +206 val_207 +206 val_207 +206 val_207 +208 val_208 +208 val_208 +208 val_208 +221 val_221 +221 val_221 +229 val_229 +229 val_229 +237 val_237 +237 val_237 +243 val_244 +243 val_244 +244 val_244 +244 val_245 +244 val_245 +244 val_245 +249 val_249 +249 val_250 +249 val_250 +252 val_252 +252 val_253 +254 val_255 +256 val_256 +256 val_256 +256 val_257 +266 val_266 +271 val_272 +272 val_272 +272 val_272 +272 val_273 +286 val_286 +286 val_287 +289 val_289 +289 val_290 +292 val_292 +292 val_293 +292 val_293 +304 val_305 +307 val_307 +307 val_307 +308 val_308 +308 val_309 +308 val_309 +315 val_315 +316 val_316 +316 val_316 +316 val_316 +317 val_317 +317 val_317 +317 val_318 +326 val_327 +327 val_327 +327 val_327 +327 val_327 +334 val_335 +336 val_336 +336 val_337 +338 val_338 +338 val_339 +339 val_339 +342 val_342 +342 val_342 +342 val_343 +344 val_344 +344 val_344 +344 val_345 +348 val_348 +348 val_348 +348 val_348 +348 val_348 +348 val_348 +348 val_349 +349 val_350 +349 val_350 +349 val_350 +349 val_350 +352 val_353 +352 val_353 +353 val_353 +353 val_353 +353 val_354 +355 val_356 +355 val_356 +360 val_360 +360 val_361 +362 val_362 +364 val_364 +364 val_365 +369 val_369 +369 val_369 +369 val_369 +369 val_370 +371 val_372 +371 val_372 +371 val_372 +371 val_372 +377 val_377 +378 val_378 +378 val_379 +391 val_392 +391 val_392 +392 val_392 +392 val_393 +392 val_393 +396 val_396 +396 val_396 +396 val_396 +399 val_399 +399 val_399 +399 val_400 +399 val_400 +402 val_402 +402 val_403 +402 val_403 +402 val_403 +404 val_404 +404 val_404 +404 val_405 +404 val_405 +404 val_405 +407 val_407 +407 val_408 +407 val_408 +407 val_408 +408 val_409 +408 val_409 +410 val_411 +417 val_417 +417 val_417 +417 val_417 +419 val_419 +423 val_424 +426 val_427 +427 val_427 +427 val_428 +427 val_428 +440 val_441 +440 val_441 +449 val_449 +452 val_452 +458 val_458 +458 val_458 +463 val_463 +463 val_463 +463 val_464 +466 val_466 +466 val_466 +466 val_466 +472 val_472 +476 val_477 +476 val_477 +478 val_478 +478 val_478 +478 val_479 +478 val_479 +479 val_479 +482 val_482 +482 val_483 +484 val_484 +484 val_485 +497 val_497 +497 val_498 +497 val_498 diff --git ql/src/test/results/clientpositive/llap/sample8.q.out ql/src/test/results/clientpositive/llap/sample8.q.out new file mode 100644 index 0000000000..cda918e8c4 --- /dev/null +++ ql/src/test/results/clientpositive/llap/sample8.q.out @@ -0,0 +1,957 @@ +PREHOOK: query: EXPLAIN EXTENDED +SELECT s.* +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN EXTENDED +SELECT s.* +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((((hash(key) & 2147483647) % 10) = 0) and value is not null and (((hash(key) & 2147483647) % 1) = 0)) (type: boolean) + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: key (type: string), value (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [s] + Map 3 + Map Operator Tree: + TableScan + alias: t + Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((((hash(key) & 2147483647) % 1) = 0) and value is not null and (((hash(key) & 2147483647) % 10) = 0)) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + key expressions: key (type: string), value (type: string) + null sort order: zz + numBuckets: -1 + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + tag: 1 + auto parallelism: true + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 11 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-09 + hr 12 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [t] + /srcpart/ds=2008-04-08/hr=12 [t] + /srcpart/ds=2008-04-09/hr=11 [t] + /srcpart/ds=2008-04-09/hr=12 [t] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string), value (type: string) + 1 key (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col7, _col8 + Position of Big Table: 1 + Statistics: Num rows: 197 Data size: 70132 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + isSamplingPred: false + predicate: ((_col7 = _col0) and (_col8 = _col1)) (type: boolean) + Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT s.key, s.value +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: SELECT s.key, s.value +FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s +JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t +WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 +#### A masked pattern was here #### +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +149 val_149 +196 val_196 +196 val_196 +196 val_196 +196 val_196 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +219 val_219 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +238 val_238 +258 val_258 +258 val_258 +258 val_258 +258 val_258 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +280 val_280 +285 val_285 +285 val_285 +285 val_285 +285 val_285 +291 val_291 +291 val_291 +291 val_291 +291 val_291 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +298 val_298 +306 val_306 +306 val_306 +306 val_306 +306 val_306 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +37 val_37 +374 val_374 +374 val_374 +374 val_374 +374 val_374 +377 val_377 +377 val_377 +377 val_377 +377 val_377 +394 val_394 +394 val_394 +394 val_394 +394 val_394 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +406 val_406 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +414 val_414 +444 val_444 +444 val_444 +444 val_444 +444 val_444 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +458 val_458 +485 val_485 +485 val_485 +485 val_485 +485 val_485 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +492 val_492 +66 val_66 +66 val_66 +66 val_66 +66 val_66 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +67 val_67 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +72 val_72 +8 val_8 +8 val_8 +8 val_8 +8 val_8 +86 val_86 +86 val_86 +86 val_86 +86 val_86 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +97 val_97 +PREHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Row Limit Per Split: 100 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Row Limit Per Split: 10 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +238 val_238 238 val_238 +255 val_255 255 val_255 +278 val_278 278 val_278 +311 val_311 311 val_311 +311 val_311 311 val_311 +98 val_98 98 val_98 +PREHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Row Limit Per Split: 100 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Row Limit Per Split: 10 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 = _col5) (type: boolean) + Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +238 val_238 238 val_238 +255 val_255 255 val_255 +278 val_278 278 val_278 +311 val_311 311 val_311 +311 val_311 311 val_311 +98 val_98 98 val_98 diff --git ql/src/test/results/clientpositive/sample9.q.out ql/src/test/results/clientpositive/llap/sample9.q.out similarity index 59% rename from ql/src/test/results/clientpositive/sample9.q.out rename to ql/src/test/results/clientpositive/llap/sample9.q.out index 968ba801c8..8e13e25fb4 100644 --- ql/src/test/results/clientpositive/sample9.q.out +++ ql/src/test/results/clientpositive/llap/sample9.q.out @@ -11,112 +11,24 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - sampleDesc: BUCKET 1 OUT OF 2 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s:a] - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: a + GatherStats: false + Filter Operator + isSamplingPred: true + predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) + sampleDesc: BUCKET 1 OUT OF 2 + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: SELECT s.* FROM (SELECT a.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 2 on key) a) s diff --git ql/src/test/results/clientpositive/llap/select_as_omitted.q.out ql/src/test/results/clientpositive/llap/select_as_omitted.q.out new file mode 100644 index 0000000000..4547fb7555 --- /dev/null +++ ql/src/test/results/clientpositive/llap/select_as_omitted.q.out @@ -0,0 +1,95 @@ +PREHOOK: query: EXPLAIn +SELECT a, b FROM ( + SELECT key a, value b + FROM src +) src1 +ORDER BY a LIMIT 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIn +SELECT a, b FROM ( + SELECT key a, value b + FROM src +) src1 +ORDER BY a LIMIT 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: key (type: string) + null sort order: z + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 1 + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a, b FROM ( + SELECT key a, value b + FROM src +) src1 +ORDER BY a LIMIT 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT a, b FROM ( + SELECT key a, value b + FROM src +) src1 +ORDER BY a LIMIT 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 diff --git ql/src/test/results/clientpositive/llap/select_column_pruning.q.out ql/src/test/results/clientpositive/llap/select_column_pruning.q.out new file mode 100644 index 0000000000..bd97aebc4d --- /dev/null +++ ql/src/test/results/clientpositive/llap/select_column_pruning.q.out @@ -0,0 +1,168 @@ +PREHOOK: query: CREATE TABLE lv_table1( c1 STRING, c2 ARRAY, c3 INT, c4 CHAR(1), c5 STRING, c6 STRING, c7 STRING, c8 STRING, c9 STRING, c10 STRING, c11 STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@lv_table1 +POSTHOOK: query: CREATE TABLE lv_table1( c1 STRING, c2 ARRAY, c3 INT, c4 CHAR(1), c5 STRING, c6 STRING, c7 STRING, c8 STRING, c9 STRING, c10 STRING, c11 STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@lv_table1 +PREHOOK: query: INSERT OVERWRITE TABLE lv_table1 SELECT 'abc ', array(1,2,3), 100, 't', 'test', 'test', 'test', 'test', 'test', 'test', 'test' FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@lv_table1 +POSTHOOK: query: INSERT OVERWRITE TABLE lv_table1 SELECT 'abc ', array(1,2,3), 100, 't', 'test', 'test', 'test', 'test', 'test', 'test', 'test' FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@lv_table1 +POSTHOOK: Lineage: lv_table1.c1 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c10 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c11 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c2 EXPRESSION [] +POSTHOOK: Lineage: lv_table1.c3 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c4 EXPRESSION [] +POSTHOOK: Lineage: lv_table1.c5 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c6 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c7 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c8 SIMPLE [] +POSTHOOK: Lineage: lv_table1.c9 SIMPLE [] +PREHOOK: query: EXPLAIN SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@lv_table1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@lv_table1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: lv_table1 + filterExpr: (c3 = 100) (type: boolean) + Statistics: Num rows: 500 Data size: 800156 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (c3 = 100) (type: boolean) + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c1 (type: string), c2 (type: array), c4 (type: char(1)), c5 (type: string), c6 (type: string), c7 (type: string), c8 (type: string), c9 (type: string), c10 (type: string), c11 (type: string) + outputColumnNames: c1, c2, c4, c5, c6, c7, c8, c9, c10, c11 + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14 + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + Top N Key Operator + sort order: ++ + keys: _col0 (type: string), _col14 (type: int) + null sort order: zz + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + top n: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col14 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col11 (type: int) + null sort order: zz + sort order: ++ + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) + Select Operator + expressions: array(1,2,3) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14 + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + Top N Key Operator + sort order: ++ + keys: _col0 (type: string), _col14 (type: int) + null sort order: zz + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + top n: 1 + Select Operator + expressions: _col0 (type: string), _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col14 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col11 (type: int) + null sort order: zz + sort order: ++ + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), VALUE._col2 (type: char(1)), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + Top N Key Operator + sort order: ++ + keys: _col0 (type: string), _col11 (type: int) + null sort order: zz + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + top n: 1 + Reduce Output Operator + key expressions: _col0 (type: string), _col11 (type: int) + null sort order: zz + sort order: ++ + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), 100 (type: int), VALUE._col2 (type: char(1)), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 1 + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@lv_table1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@lv_table1 +#### A masked pattern was here #### +abc [1,2,3] 100 t test test test test test test test 1 diff --git ql/src/test/results/clientpositive/select_same_col.q.out ql/src/test/results/clientpositive/llap/select_same_col.q.out similarity index 98% rename from ql/src/test/results/clientpositive/select_same_col.q.out rename to ql/src/test/results/clientpositive/llap/select_same_col.q.out index b03b3de104..3cd4f7cbb1 100644 --- ql/src/test/results/clientpositive/select_same_col.q.out +++ ql/src/test/results/clientpositive/llap/select_same_col.q.out @@ -22,16 +22,16 @@ POSTHOOK: query: select cast(value as binary), value from srclimit POSTHOOK: type: QUERY POSTHOOK: Input: default@srclimit #### A masked pattern was here #### -val_484 val_484 -val_98 val_98 -val_278 val_278 -val_255 val_255 -val_409 val_409 val_165 val_165 +val_238 val_238 +val_255 val_255 val_27 val_27 +val_278 val_278 val_311 val_311 +val_409 val_409 +val_484 val_484 val_86 val_86 -val_238 val_238 +val_98 val_98 PREHOOK: query: select cast(value as binary), value from srclimit order by value PREHOOK: type: QUERY PREHOOK: Input: default@srclimit @@ -63,11 +63,11 @@ val_238 val_238 val_255 val_255 val_27 val_27 val_278 val_278 -PREHOOK: query: select cast(value as binary), value, key from srclimit order by value limit 5 +PREHOOK: query: select cast(value as binary), value, key from srclimit order by value, key limit 5 PREHOOK: type: QUERY PREHOOK: Input: default@srclimit #### A masked pattern was here #### -POSTHOOK: query: select cast(value as binary), value, key from srclimit order by value limit 5 +POSTHOOK: query: select cast(value as binary), value, key from srclimit order by value, key limit 5 POSTHOOK: type: QUERY POSTHOOK: Input: default@srclimit #### A masked pattern was here #### @@ -84,16 +84,16 @@ POSTHOOK: query: select *, key, value from srclimit POSTHOOK: type: QUERY POSTHOOK: Input: default@srclimit #### A masked pattern was here #### -484 val_484 484 val_484 -98 val_98 98 val_98 -278 val_278 278 val_278 -255 val_255 255 val_255 -409 val_409 409 val_409 165 val_165 165 val_165 +238 val_238 238 val_238 +255 val_255 255 val_255 27 val_27 27 val_27 +278 val_278 278 val_278 311 val_311 311 val_311 +409 val_409 409 val_409 +484 val_484 484 val_484 86 val_86 86 val_86 -238 val_238 238 val_238 +98 val_98 98 val_98 PREHOOK: query: select * from (select *, key, value from srclimit) t PREHOOK: type: QUERY PREHOOK: Input: default@srclimit @@ -102,16 +102,16 @@ POSTHOOK: query: select * from (select *, key, value from srclimit) t POSTHOOK: type: QUERY POSTHOOK: Input: default@srclimit #### A masked pattern was here #### -484 val_484 484 val_484 -98 val_98 98 val_98 -278 val_278 278 val_278 -255 val_255 255 val_255 -409 val_409 409 val_409 165 val_165 165 val_165 +238 val_238 238 val_238 +255 val_255 255 val_255 27 val_27 27 val_27 +278 val_278 278 val_278 311 val_311 311 val_311 +409 val_409 409 val_409 +484 val_484 484 val_484 86 val_86 86 val_86 -238 val_238 238 val_238 +98 val_98 98 val_98 PREHOOK: query: drop table srclimit PREHOOK: type: DROPTABLE PREHOOK: Input: default@srclimit diff --git ql/src/test/results/clientpositive/select_unquote_and.q.out ql/src/test/results/clientpositive/llap/select_unquote_and.q.out similarity index 72% rename from ql/src/test/results/clientpositive/select_unquote_and.q.out rename to ql/src/test/results/clientpositive/llap/select_unquote_and.q.out index 23aeccfc21..54e002dbbc 100644 --- ql/src/test/results/clientpositive/select_unquote_and.q.out +++ ql/src/test/results/clientpositive/llap/select_unquote_and.q.out @@ -52,38 +52,22 @@ POSTHOOK: Input: default@npe_test_n0@ds=2012-12-11 POSTHOOK: Input: default@npe_test_n0@ds=2012-12-12 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: npe_test_n0 - filterExpr: ((UDFToDouble(ds) > 1970.0D) and (UDFToDouble(ds) < 1985.0D)) (type: boolean) - Statistics: Num rows: 498 Data size: 180276 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(ds) > 1970.0D) and (UDFToDouble(ds) < 1985.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 19910 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: npe_test_n0 + filterExpr: ((UDFToDouble(ds) > 1970.0D) and (UDFToDouble(ds) < 1985.0D)) (type: boolean) + Filter Operator + predicate: ((UDFToDouble(ds) > 1970.0D) and (UDFToDouble(ds) < 1985.0D)) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink PREHOOK: query: SELECT count(*) FROM npe_test_n0 WHERE ds > 2012-11-31 AND ds < 2012-12-15 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/select_unquote_not.q.out ql/src/test/results/clientpositive/llap/select_unquote_not.q.out similarity index 73% rename from ql/src/test/results/clientpositive/select_unquote_not.q.out rename to ql/src/test/results/clientpositive/llap/select_unquote_not.q.out index e5d7e76f3f..d299bea3c2 100644 --- ql/src/test/results/clientpositive/select_unquote_not.q.out +++ ql/src/test/results/clientpositive/llap/select_unquote_not.q.out @@ -52,38 +52,22 @@ POSTHOOK: Input: default@npe_test_n1@ds=2012-12-11 POSTHOOK: Input: default@npe_test_n1@ds=2012-12-12 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: npe_test_n1 - filterExpr: (UDFToDouble(ds) >= 1970.0D) (type: boolean) - Statistics: Num rows: 498 Data size: 180276 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(ds) >= 1970.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 60092 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: npe_test_n1 + filterExpr: (UDFToDouble(ds) >= 1970.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(ds) >= 1970.0D) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink PREHOOK: query: SELECT count(*) FROM npe_test_n1 WHERE NOT ds < 2012-11-31 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/select_unquote_or.q.out ql/src/test/results/clientpositive/llap/select_unquote_or.q.out similarity index 72% rename from ql/src/test/results/clientpositive/select_unquote_or.q.out rename to ql/src/test/results/clientpositive/llap/select_unquote_or.q.out index bb4df3926e..1cba4cd23f 100644 --- ql/src/test/results/clientpositive/select_unquote_or.q.out +++ ql/src/test/results/clientpositive/llap/select_unquote_or.q.out @@ -52,38 +52,22 @@ POSTHOOK: Input: default@npe_test@ds=2012-12-11 POSTHOOK: Input: default@npe_test@ds=2012-12-12 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: npe_test - filterExpr: UDFToDouble(ds) NOT BETWEEN 1985.0D AND 1970.0D (type: boolean) - Statistics: Num rows: 498 Data size: 180276 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: UDFToDouble(ds) NOT BETWEEN 1985.0D AND 1970.0D (type: boolean) - Statistics: Num rows: 443 Data size: 160366 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 443 Data size: 160366 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 443 Data size: 160366 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: npe_test + filterExpr: UDFToDouble(ds) NOT BETWEEN 1985.0D AND 1970.0D (type: boolean) + Filter Operator + predicate: UDFToDouble(ds) NOT BETWEEN 1985.0D AND 1970.0D (type: boolean) + Select Operator + expressions: key (type: string), value (type: string), ds (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink PREHOOK: query: SELECT count(*) FROM npe_test WHERE ds > 2012-11-31 OR ds < 2012-12-15 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/semijoin2.q.out ql/src/test/results/clientpositive/llap/semijoin2.q.out new file mode 100644 index 0000000000..ea3388a04c --- /dev/null +++ ql/src/test/results/clientpositive/llap/semijoin2.q.out @@ -0,0 +1,288 @@ +PREHOOK: query: CREATE TABLE table_1_n0 (boolean_col_1 BOOLEAN, float_col_2 FLOAT, bigint_col_3 BIGINT, varchar0111_col_4 VARCHAR(111), bigint_col_5 BIGINT, float_col_6 FLOAT, boolean_col_7 BOOLEAN, decimal0101_col_8 DECIMAL(1, 1), decimal0904_col_9 DECIMAL(9, 4), char0112_col_10 CHAR(112), double_col_11 DOUBLE, boolean_col_12 BOOLEAN, double_col_13 DOUBLE, varchar0142_col_14 VARCHAR(142), timestamp_col_15 TIMESTAMP, decimal0502_col_16 DECIMAL(5, 2), smallint_col_25 SMALLINT, decimal3222_col_18 DECIMAL(32, 22), boolean_col_19 BOOLEAN, decimal2012_col_20 DECIMAL(20, 12), char0204_col_21 CHAR(204), double_col_61 DOUBLE, timestamp_col_23 TIMESTAMP, int_col_24 INT, float_col_25 FLOAT, smallint_col_26 SMALLINT, double_col_27 DOUBLE, char0180_col_28 CHAR(180), decimal1503_col_29 DECIMAL(15, 3), timestamp_col_30 TIMESTAMP, smallint_col_31 SMALLINT, decimal2020_col_32 DECIMAL(20, 20), timestamp_col_33 TIMESTAMP, boolean_col_34 BOOLEAN, decimal3025_col_35 DECIMAL(30, 25), decimal3117_col_36 DECIMAL(31, 17), timestamp_col_37 TIMESTAMP, varchar0146_col_38 VARCHAR(146), boolean_col_39 BOOLEAN, double_col_40 DOUBLE, float_col_41 FLOAT, timestamp_col_42 TIMESTAMP, double_col_43 DOUBLE, boolean_col_44 BOOLEAN, timestamp_col_45 TIMESTAMP, tinyint_col_8 TINYINT, int_col_47 INT, decimal0401_col_48 DECIMAL(4, 1), varchar0064_col_49 VARCHAR(64), string_col_50 STRING, double_col_51 DOUBLE, string_col_52 STRING, boolean_col_53 BOOLEAN, int_col_54 INT, boolean_col_55 BOOLEAN, string_col_56 STRING, double_col_57 DOUBLE, varchar0131_col_58 VARCHAR(131), boolean_col_59 BOOLEAN, bigint_col_22 BIGINT, char0184_col_61 CHAR(184), varchar0173_col_62 VARCHAR(173), timestamp_col_63 TIMESTAMP, decimal1709_col_26 DECIMAL(20, 5), timestamp_col_65 TIMESTAMP, timestamp_col_66 TIMESTAMP, timestamp_col_67 TIMESTAMP, boolean_col_68 BOOLEAN, decimal1208_col_20 DECIMAL(33, 11), decimal1605_col_70 DECIMAL(16, 5), varchar0010_col_71 VARCHAR(10), tinyint_col_72 TINYINT, timestamp_col_10 TIMESTAMP, decimal2714_col_74 DECIMAL(27, 14), double_col_75 DOUBLE, boolean_col_76 BOOLEAN, double_col_77 DOUBLE, string_col_78 STRING, boolean_col_79 BOOLEAN, boolean_col_80 BOOLEAN, decimal0803_col_81 DECIMAL(8, 3), decimal1303_col_82 DECIMAL(13, 3), tinyint_col_83 TINYINT, decimal3424_col_84 DECIMAL(34, 24), float_col_85 FLOAT, boolean_col_86 BOOLEAN, char0233_col_87 CHAR(233)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@table_1_n0 +POSTHOOK: query: CREATE TABLE table_1_n0 (boolean_col_1 BOOLEAN, float_col_2 FLOAT, bigint_col_3 BIGINT, varchar0111_col_4 VARCHAR(111), bigint_col_5 BIGINT, float_col_6 FLOAT, boolean_col_7 BOOLEAN, decimal0101_col_8 DECIMAL(1, 1), decimal0904_col_9 DECIMAL(9, 4), char0112_col_10 CHAR(112), double_col_11 DOUBLE, boolean_col_12 BOOLEAN, double_col_13 DOUBLE, varchar0142_col_14 VARCHAR(142), timestamp_col_15 TIMESTAMP, decimal0502_col_16 DECIMAL(5, 2), smallint_col_25 SMALLINT, decimal3222_col_18 DECIMAL(32, 22), boolean_col_19 BOOLEAN, decimal2012_col_20 DECIMAL(20, 12), char0204_col_21 CHAR(204), double_col_61 DOUBLE, timestamp_col_23 TIMESTAMP, int_col_24 INT, float_col_25 FLOAT, smallint_col_26 SMALLINT, double_col_27 DOUBLE, char0180_col_28 CHAR(180), decimal1503_col_29 DECIMAL(15, 3), timestamp_col_30 TIMESTAMP, smallint_col_31 SMALLINT, decimal2020_col_32 DECIMAL(20, 20), timestamp_col_33 TIMESTAMP, boolean_col_34 BOOLEAN, decimal3025_col_35 DECIMAL(30, 25), decimal3117_col_36 DECIMAL(31, 17), timestamp_col_37 TIMESTAMP, varchar0146_col_38 VARCHAR(146), boolean_col_39 BOOLEAN, double_col_40 DOUBLE, float_col_41 FLOAT, timestamp_col_42 TIMESTAMP, double_col_43 DOUBLE, boolean_col_44 BOOLEAN, timestamp_col_45 TIMESTAMP, tinyint_col_8 TINYINT, int_col_47 INT, decimal0401_col_48 DECIMAL(4, 1), varchar0064_col_49 VARCHAR(64), string_col_50 STRING, double_col_51 DOUBLE, string_col_52 STRING, boolean_col_53 BOOLEAN, int_col_54 INT, boolean_col_55 BOOLEAN, string_col_56 STRING, double_col_57 DOUBLE, varchar0131_col_58 VARCHAR(131), boolean_col_59 BOOLEAN, bigint_col_22 BIGINT, char0184_col_61 CHAR(184), varchar0173_col_62 VARCHAR(173), timestamp_col_63 TIMESTAMP, decimal1709_col_26 DECIMAL(20, 5), timestamp_col_65 TIMESTAMP, timestamp_col_66 TIMESTAMP, timestamp_col_67 TIMESTAMP, boolean_col_68 BOOLEAN, decimal1208_col_20 DECIMAL(33, 11), decimal1605_col_70 DECIMAL(16, 5), varchar0010_col_71 VARCHAR(10), tinyint_col_72 TINYINT, timestamp_col_10 TIMESTAMP, decimal2714_col_74 DECIMAL(27, 14), double_col_75 DOUBLE, boolean_col_76 BOOLEAN, double_col_77 DOUBLE, string_col_78 STRING, boolean_col_79 BOOLEAN, boolean_col_80 BOOLEAN, decimal0803_col_81 DECIMAL(8, 3), decimal1303_col_82 DECIMAL(13, 3), tinyint_col_83 TINYINT, decimal3424_col_84 DECIMAL(34, 24), float_col_85 FLOAT, boolean_col_86 BOOLEAN, char0233_col_87 CHAR(233)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@table_1_n0 +PREHOOK: query: CREATE TABLE table_18_n0 (timestamp_col_1 TIMESTAMP, double_col_2 DOUBLE, boolean_col_3 BOOLEAN, timestamp_col_4 TIMESTAMP, decimal2103_col_5 DECIMAL(21, 3), char0221_col_6 CHAR(221), tinyint_col_7 TINYINT, float_col_8 FLOAT, int_col_2 INT, timestamp_col_10 TIMESTAMP, char0228_col_11 CHAR(228), timestamp_col_12 TIMESTAMP, double_col_13 DOUBLE, tinyint_col_6 TINYINT, tinyint_col_33 TINYINT, smallint_col_38 SMALLINT, boolean_col_17 BOOLEAN, double_col_18 DOUBLE, boolean_col_19 BOOLEAN, bigint_col_20 BIGINT, decimal0504_col_37 DECIMAL(37, 34), boolean_col_22 BOOLEAN, double_col_23 DOUBLE, timestamp_col_24 TIMESTAMP, varchar0076_col_25 VARCHAR(76), timestamp_col_18 TIMESTAMP, boolean_col_27 BOOLEAN, decimal1611_col_22 DECIMAL(37, 5), boolean_col_29 BOOLEAN) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@table_18_n0 +POSTHOOK: query: CREATE TABLE table_18_n0 (timestamp_col_1 TIMESTAMP, double_col_2 DOUBLE, boolean_col_3 BOOLEAN, timestamp_col_4 TIMESTAMP, decimal2103_col_5 DECIMAL(21, 3), char0221_col_6 CHAR(221), tinyint_col_7 TINYINT, float_col_8 FLOAT, int_col_2 INT, timestamp_col_10 TIMESTAMP, char0228_col_11 CHAR(228), timestamp_col_12 TIMESTAMP, double_col_13 DOUBLE, tinyint_col_6 TINYINT, tinyint_col_33 TINYINT, smallint_col_38 SMALLINT, boolean_col_17 BOOLEAN, double_col_18 DOUBLE, boolean_col_19 BOOLEAN, bigint_col_20 BIGINT, decimal0504_col_37 DECIMAL(37, 34), boolean_col_22 BOOLEAN, double_col_23 DOUBLE, timestamp_col_24 TIMESTAMP, varchar0076_col_25 VARCHAR(76), timestamp_col_18 TIMESTAMP, boolean_col_27 BOOLEAN, decimal1611_col_22 DECIMAL(37, 5), boolean_col_29 BOOLEAN) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@table_18_n0 +PREHOOK: query: explain +SELECT +COALESCE(498, LEAD(COALESCE(-973, -684, 515)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25), FLOOR(t1.double_col_61) DESC), 524) AS int_col, +(t2.int_col_2) + (t1.smallint_col_25) AS int_col_1, +FLOOR(t1.double_col_61) AS float_col, +COALESCE(SUM(COALESCE(62, -380, -435)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25) DESC, FLOOR(t1.double_col_61) DESC ROWS BETWEEN UNBOUNDED PRECEDING AND 48 FOLLOWING), 704) AS int_col_2 +FROM table_1_n0 t1 +INNER JOIN table_18_n0 t2 ON (((t2.tinyint_col_6) = (t1.bigint_col_22)) AND ((t2.decimal0504_col_37) = (t1.decimal1709_col_26))) AND ((t2.tinyint_col_33) = (t1.tinyint_col_8)) +WHERE +(t2.smallint_col_38) IN (SELECT +COALESCE(-92, -994) AS int_col +FROM table_1_n0 tt1 +INNER JOIN table_18_n0 tt2 ON (tt2.decimal1611_col_22) = (tt1.decimal1208_col_20) +WHERE +(t1.timestamp_col_10) = (tt2.timestamp_col_18)) +PREHOOK: type: QUERY +PREHOOK: Input: default@table_18_n0 +PREHOOK: Input: default@table_1_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain +SELECT +COALESCE(498, LEAD(COALESCE(-973, -684, 515)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25), FLOOR(t1.double_col_61) DESC), 524) AS int_col, +(t2.int_col_2) + (t1.smallint_col_25) AS int_col_1, +FLOOR(t1.double_col_61) AS float_col, +COALESCE(SUM(COALESCE(62, -380, -435)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25) DESC, FLOOR(t1.double_col_61) DESC ROWS BETWEEN UNBOUNDED PRECEDING AND 48 FOLLOWING), 704) AS int_col_2 +FROM table_1_n0 t1 +INNER JOIN table_18_n0 t2 ON (((t2.tinyint_col_6) = (t1.bigint_col_22)) AND ((t2.decimal0504_col_37) = (t1.decimal1709_col_26))) AND ((t2.tinyint_col_33) = (t1.tinyint_col_8)) +WHERE +(t2.smallint_col_38) IN (SELECT +COALESCE(-92, -994) AS int_col +FROM table_1_n0 tt1 +INNER JOIN table_18_n0 tt2 ON (tt2.decimal1611_col_22) = (tt1.decimal1208_col_20) +WHERE +(t1.timestamp_col_10) = (tt2.timestamp_col_18)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@table_18_n0 +POSTHOOK: Input: default@table_1_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 8 <- Map 7 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: (bigint_col_22 is not null and decimal1709_col_26 is not null and tinyint_col_8 is not null and timestamp_col_10 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (bigint_col_22 is not null and decimal1709_col_26 is not null and tinyint_col_8 is not null and timestamp_col_10 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + value expressions: smallint_col_25 (type: smallint), double_col_61 (type: double), timestamp_col_10 (type: timestamp) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null and tinyint_col_33 is not null and UDFToInteger(smallint_col_38) is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null and tinyint_col_33 is not null and UDFToInteger(smallint_col_38) is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + value expressions: int_col_2 (type: int), smallint_col_38 (type: smallint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 7 + Map Operator Tree: + TableScan + alias: tt1 + filterExpr: decimal1208_col_20 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: decimal1208_col_20 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: decimal1208_col_20 (type: decimal(38,6)) + null sort order: z + sort order: + + Map-reduce partition columns: decimal1208_col_20 (type: decimal(38,6)) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 9 + Map Operator Tree: + TableScan + alias: tt2 + filterExpr: (decimal1611_col_22 is not null and timestamp_col_18 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (decimal1611_col_22 is not null and timestamp_col_18 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: decimal1611_col_22 (type: decimal(38,6)) + null sort order: z + sort order: + + Map-reduce partition columns: decimal1611_col_22 (type: decimal(38,6)) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + value expressions: timestamp_col_18 (type: timestamp) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) + 1 UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) + outputColumnNames: _col16, _col21, _col72, _col98, _col105 + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToInteger(_col105) (type: int), _col72 (type: timestamp) + null sort order: zz + sort order: ++ + Map-reduce partition columns: UDFToInteger(_col105) (type: int), _col72 (type: timestamp) + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE + value expressions: _col16 (type: smallint), _col21 (type: double), _col98 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 UDFToInteger(_col105) (type: int), _col72 (type: timestamp) + 1 -92 (type: int), _col1 (type: timestamp) + outputColumnNames: _col16, _col21, _col98 + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (_col98 + _col16) (type: int), floor(_col21) (type: bigint) + null sort order: zz + sort order: +- + Map-reduce partition columns: (_col98 + _col16) (type: int) + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col16 (type: smallint), _col21 (type: double), _col98 (type: int) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col16 (type: smallint), VALUE._col21 (type: double), VALUE._col98 (type: int) + outputColumnNames: _col16, _col21, _col98 + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col16: smallint, _col21: double, _col98: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: (_col98 + _col16) ASC NULLS LAST, floor(_col21) DESC NULLS LAST + partition by: (_col98 + _col16) + raw input shape: + window functions: + window function definition + alias: LEAD_window_0 + arguments: COALESCE(-973,-684,515) + name: LEAD + window function: GenericUDAFLeadEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: LEAD_window_0 (type: int), _col16 (type: smallint), _col21 (type: double), _col98 (type: int) + outputColumnNames: LEAD_window_0, _col16, _col21, _col98 + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (_col98 + _col16) (type: int), floor(_col21) (type: bigint) + null sort order: zz + sort order: -- + Map-reduce partition columns: (_col98 + _col16) (type: int) + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + value expressions: LEAD_window_0 (type: int), _col16 (type: smallint), _col21 (type: double), _col98 (type: int) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col17 (type: smallint), VALUE._col22 (type: double), VALUE._col99 (type: int) + outputColumnNames: _col0, _col17, _col22, _col99 + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: int, _col17: smallint, _col22: double, _col99: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: (_col99 + _col17) DESC NULLS LAST, floor(_col22) DESC NULLS LAST + partition by: (_col99 + _col17) + raw input shape: + window functions: + window function definition + alias: SUM_window_1 + arguments: COALESCE(62,-380,-435) + name: SUM + window function: GenericUDAFSumLong + window frame: ROWS PRECEDING(MAX)~FOLLOWING(48) + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: COALESCE(498,_col0,524) (type: int), (_col99 + _col17) (type: int), floor(_col22) (type: bigint), COALESCE(SUM_window_1,704) (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 8 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 decimal1208_col_20 (type: decimal(38,6)) + 1 decimal1611_col_22 (type: decimal(38,6)) + outputColumnNames: _col115 + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col115 (type: timestamp) + outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: -92 (type: int), _col1 (type: timestamp) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: -92 (type: int), _col1 (type: timestamp) + null sort order: zz + sort order: ++ + Map-reduce partition columns: -92 (type: int), _col1 (type: timestamp) + Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/semijoin3.q.out ql/src/test/results/clientpositive/llap/semijoin3.q.out new file mode 100644 index 0000000000..bb29ae3540 --- /dev/null +++ ql/src/test/results/clientpositive/llap/semijoin3.q.out @@ -0,0 +1,177 @@ +PREHOOK: query: create table t1_n59 as select cast(key as int) key, value from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@t1_n59 +POSTHOOK: query: create table t1_n59 as select cast(key as int) key, value from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1_n59 +POSTHOOK: Lineage: t1_n59.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: t1_n59.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: create table t2_n37 as select cast(key as int) key, value from src +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@t2_n37 +POSTHOOK: query: create table t2_n37 as select cast(key as int) key, value from src +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t2_n37 +POSTHOOK: Lineage: t2_n37.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: t2_n37.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain +select count(1) +from + (select key + from t1_n59 + where key = 0) t1_n59 +left semi join + (select key + from t2_n37 + where key = 0) t2_n37 +on 1 = 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n59 +PREHOOK: Input: default@t2_n37 +#### A masked pattern was here #### +POSTHOOK: query: explain +select count(1) +from + (select key + from t1_n59 + where key = 0) t1_n59 +left semi join + (select key + from t2_n37 + where key = 0) t2_n37 +on 1 = 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n59 +POSTHOOK: Input: default@t2_n37 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n59 + filterExpr: (key = 0) (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: 1 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: t2_n37 + filterExpr: (key = 0) (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 0) (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: 1 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 1 (type: int) + 1 1 (type: int) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(1) +from + (select key + from t1_n59 + where key = 0) t1_n59 +left semi join + (select key + from t2_n37 + where key = 0) t2_n37 +on 1 = 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n59 +PREHOOK: Input: default@t2_n37 +#### A masked pattern was here #### +POSTHOOK: query: select count(1) +from + (select key + from t1_n59 + where key = 0) t1_n59 +left semi join + (select key + from t2_n37 + where key = 0) t2_n37 +on 1 = 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n59 +POSTHOOK: Input: default@t2_n37 +#### A masked pattern was here #### +3 diff --git ql/src/test/results/clientpositive/llap/semijoin4.q.out ql/src/test/results/clientpositive/llap/semijoin4.q.out new file mode 100644 index 0000000000..7b51a63904 --- /dev/null +++ ql/src/test/results/clientpositive/llap/semijoin4.q.out @@ -0,0 +1,240 @@ +PREHOOK: query: CREATE TABLE table_1 (int_col_1 INT, decimal3003_col_2 DECIMAL(30, 3), timestamp_col_3 TIMESTAMP, decimal0101_col_4 DECIMAL(1, 1), double_col_5 DOUBLE, boolean_col_6 BOOLEAN, timestamp_col_7 TIMESTAMP, varchar0098_col_8 VARCHAR(98), int_col_9 INT, timestamp_col_10 TIMESTAMP, decimal0903_col_11 DECIMAL(9, 3), int_col_12 INT, bigint_col_13 BIGINT, boolean_col_14 BOOLEAN, char0254_col_15 CHAR(254), boolean_col_16 BOOLEAN, smallint_col_17 SMALLINT, float_col_18 FLOAT, decimal2608_col_19 DECIMAL(26, 8), varchar0216_col_20 VARCHAR(216), string_col_21 STRING, timestamp_col_22 TIMESTAMP, double_col_23 DOUBLE, smallint_col_24 SMALLINT, float_col_25 FLOAT, decimal2016_col_26 DECIMAL(20, 16), string_col_27 STRING, decimal0202_col_28 DECIMAL(2, 2), boolean_col_29 BOOLEAN, decimal2020_col_30 DECIMAL(20, 20), float_col_31 FLOAT, boolean_col_32 BOOLEAN, varchar0148_col_33 VARCHAR(148), decimal2121_col_34 DECIMAL(21, 21), timestamp_col_35 TIMESTAMP, float_col_36 FLOAT, float_col_37 FLOAT, string_col_38 STRING, decimal3420_col_39 DECIMAL(34, 20), smallint_col_40 SMALLINT, decimal1408_col_41 DECIMAL(14, 8), string_col_42 STRING, decimal0902_col_43 DECIMAL(9, 2), varchar0204_col_44 VARCHAR(204), float_col_45 FLOAT, tinyint_col_46 TINYINT, double_col_47 DOUBLE, timestamp_col_48 TIMESTAMP, double_col_49 DOUBLE, timestamp_col_50 TIMESTAMP, decimal0704_col_51 DECIMAL(7, 4), int_col_52 INT, double_col_53 DOUBLE, int_col_54 INT, timestamp_col_55 TIMESTAMP, decimal0505_col_56 DECIMAL(5, 5), char0155_col_57 CHAR(155), double_col_58 DOUBLE, timestamp_col_59 TIMESTAMP, double_col_60 DOUBLE, float_col_61 FLOAT, char0249_col_62 CHAR(249), float_col_63 FLOAT, smallint_col_64 SMALLINT, decimal1309_col_65 DECIMAL(13, 9), timestamp_col_66 TIMESTAMP, boolean_col_67 BOOLEAN, tinyint_col_68 TINYINT, tinyint_col_69 TINYINT, double_col_70 DOUBLE, bigint_col_71 BIGINT, boolean_col_72 BOOLEAN, float_col_73 FLOAT, char0222_col_74 CHAR(222), boolean_col_75 BOOLEAN, string_col_76 STRING, decimal2612_col_77 DECIMAL(26, 12), bigint_col_78 BIGINT, char0128_col_79 CHAR(128), tinyint_col_80 TINYINT, boolean_col_81 BOOLEAN, int_col_82 INT, boolean_col_83 BOOLEAN, decimal2622_col_84 DECIMAL(26, 22), boolean_col_85 BOOLEAN, boolean_col_86 BOOLEAN, decimal0907_col_87 DECIMAL(9, 7)) +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@table_1 +POSTHOOK: query: CREATE TABLE table_1 (int_col_1 INT, decimal3003_col_2 DECIMAL(30, 3), timestamp_col_3 TIMESTAMP, decimal0101_col_4 DECIMAL(1, 1), double_col_5 DOUBLE, boolean_col_6 BOOLEAN, timestamp_col_7 TIMESTAMP, varchar0098_col_8 VARCHAR(98), int_col_9 INT, timestamp_col_10 TIMESTAMP, decimal0903_col_11 DECIMAL(9, 3), int_col_12 INT, bigint_col_13 BIGINT, boolean_col_14 BOOLEAN, char0254_col_15 CHAR(254), boolean_col_16 BOOLEAN, smallint_col_17 SMALLINT, float_col_18 FLOAT, decimal2608_col_19 DECIMAL(26, 8), varchar0216_col_20 VARCHAR(216), string_col_21 STRING, timestamp_col_22 TIMESTAMP, double_col_23 DOUBLE, smallint_col_24 SMALLINT, float_col_25 FLOAT, decimal2016_col_26 DECIMAL(20, 16), string_col_27 STRING, decimal0202_col_28 DECIMAL(2, 2), boolean_col_29 BOOLEAN, decimal2020_col_30 DECIMAL(20, 20), float_col_31 FLOAT, boolean_col_32 BOOLEAN, varchar0148_col_33 VARCHAR(148), decimal2121_col_34 DECIMAL(21, 21), timestamp_col_35 TIMESTAMP, float_col_36 FLOAT, float_col_37 FLOAT, string_col_38 STRING, decimal3420_col_39 DECIMAL(34, 20), smallint_col_40 SMALLINT, decimal1408_col_41 DECIMAL(14, 8), string_col_42 STRING, decimal0902_col_43 DECIMAL(9, 2), varchar0204_col_44 VARCHAR(204), float_col_45 FLOAT, tinyint_col_46 TINYINT, double_col_47 DOUBLE, timestamp_col_48 TIMESTAMP, double_col_49 DOUBLE, timestamp_col_50 TIMESTAMP, decimal0704_col_51 DECIMAL(7, 4), int_col_52 INT, double_col_53 DOUBLE, int_col_54 INT, timestamp_col_55 TIMESTAMP, decimal0505_col_56 DECIMAL(5, 5), char0155_col_57 CHAR(155), double_col_58 DOUBLE, timestamp_col_59 TIMESTAMP, double_col_60 DOUBLE, float_col_61 FLOAT, char0249_col_62 CHAR(249), float_col_63 FLOAT, smallint_col_64 SMALLINT, decimal1309_col_65 DECIMAL(13, 9), timestamp_col_66 TIMESTAMP, boolean_col_67 BOOLEAN, tinyint_col_68 TINYINT, tinyint_col_69 TINYINT, double_col_70 DOUBLE, bigint_col_71 BIGINT, boolean_col_72 BOOLEAN, float_col_73 FLOAT, char0222_col_74 CHAR(222), boolean_col_75 BOOLEAN, string_col_76 STRING, decimal2612_col_77 DECIMAL(26, 12), bigint_col_78 BIGINT, char0128_col_79 CHAR(128), tinyint_col_80 TINYINT, boolean_col_81 BOOLEAN, int_col_82 INT, boolean_col_83 BOOLEAN, decimal2622_col_84 DECIMAL(26, 22), boolean_col_85 BOOLEAN, boolean_col_86 BOOLEAN, decimal0907_col_87 DECIMAL(9, 7)) +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@table_1 +PREHOOK: query: CREATE TABLE table_18 (float_col_1 FLOAT, double_col_2 DOUBLE, decimal2518_col_3 DECIMAL(25, 18), boolean_col_4 BOOLEAN, bigint_col_5 BIGINT, boolean_col_6 BOOLEAN, boolean_col_7 BOOLEAN, char0035_col_8 CHAR(35), decimal2709_col_9 DECIMAL(27, 9), timestamp_col_10 TIMESTAMP, bigint_col_11 BIGINT, decimal3604_col_12 DECIMAL(36, 4), string_col_13 STRING, timestamp_col_14 TIMESTAMP, timestamp_col_15 TIMESTAMP, decimal1911_col_16 DECIMAL(19, 11), boolean_col_17 BOOLEAN, tinyint_col_18 TINYINT, timestamp_col_19 TIMESTAMP, timestamp_col_20 TIMESTAMP, tinyint_col_21 TINYINT, float_col_22 FLOAT, timestamp_col_23 TIMESTAMP) +STORED AS orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@table_18 +POSTHOOK: query: CREATE TABLE table_18 (float_col_1 FLOAT, double_col_2 DOUBLE, decimal2518_col_3 DECIMAL(25, 18), boolean_col_4 BOOLEAN, bigint_col_5 BIGINT, boolean_col_6 BOOLEAN, boolean_col_7 BOOLEAN, char0035_col_8 CHAR(35), decimal2709_col_9 DECIMAL(27, 9), timestamp_col_10 TIMESTAMP, bigint_col_11 BIGINT, decimal3604_col_12 DECIMAL(36, 4), string_col_13 STRING, timestamp_col_14 TIMESTAMP, timestamp_col_15 TIMESTAMP, decimal1911_col_16 DECIMAL(19, 11), boolean_col_17 BOOLEAN, tinyint_col_18 TINYINT, timestamp_col_19 TIMESTAMP, timestamp_col_20 TIMESTAMP, tinyint_col_21 TINYINT, float_col_22 FLOAT, timestamp_col_23 TIMESTAMP) +STORED AS orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@table_18 +Warning: Shuffle Join MERGEJOIN[79][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain +SELECT + COALESCE(498, + LEAD(COALESCE(-973, -684, 515)) OVER ( + PARTITION BY (t2.tinyint_col_21 + t1.smallint_col_24) + ORDER BY (t2.tinyint_col_21 + t1.smallint_col_24), + FLOOR(t1.double_col_60) DESC), + 524) AS int_col +FROM table_1 t1 INNER JOIN table_18 t2 +ON (((t2.tinyint_col_18) = (t1.bigint_col_13)) + AND ((t2.decimal2709_col_9) = (t1.decimal1309_col_65))) + AND ((t2.tinyint_col_21) = (t1.tinyint_col_46)) +WHERE (t2.tinyint_col_21) IN ( + SELECT COALESCE(-92, -994) AS int_col_3 + FROM table_1 tt1 INNER JOIN table_18 tt2 + ON (tt2.decimal1911_col_16) = (tt1.decimal1309_col_65) + WHERE (tt1.timestamp_col_66) = (tt2.timestamp_col_19)) +PREHOOK: type: QUERY +PREHOOK: Input: default@table_1 +PREHOOK: Input: default@table_18 +#### A masked pattern was here #### +POSTHOOK: query: explain +SELECT + COALESCE(498, + LEAD(COALESCE(-973, -684, 515)) OVER ( + PARTITION BY (t2.tinyint_col_21 + t1.smallint_col_24) + ORDER BY (t2.tinyint_col_21 + t1.smallint_col_24), + FLOOR(t1.double_col_60) DESC), + 524) AS int_col +FROM table_1 t1 INNER JOIN table_18 t2 +ON (((t2.tinyint_col_18) = (t1.bigint_col_13)) + AND ((t2.decimal2709_col_9) = (t1.decimal1309_col_65))) + AND ((t2.tinyint_col_21) = (t1.tinyint_col_46)) +WHERE (t2.tinyint_col_21) IN ( + SELECT COALESCE(-92, -994) AS int_col_3 + FROM table_1 tt1 INNER JOIN table_18 tt2 + ON (tt2.decimal1911_col_16) = (tt1.decimal1309_col_65) + WHERE (tt1.timestamp_col_66) = (tt2.timestamp_col_19)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@table_1 +POSTHOOK: Input: default@table_18 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 7 (XPROD_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) + Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: ((tinyint_col_46 = -92Y) and bigint_col_13 is not null and decimal1309_col_65 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((tinyint_col_46 = -92Y) and bigint_col_13 is not null and decimal1309_col_65 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: bigint_col_13 (type: bigint), decimal1309_col_65 (type: decimal(13,9)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: bigint), _col1 (type: decimal(27,9)) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: bigint), _col1 (type: decimal(27,9)) + Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 4 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: ((tinyint_col_21 = -92Y) and UDFToLong(tinyint_col_18) is not null and decimal2709_col_9 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((tinyint_col_21 = -92Y) and UDFToLong(tinyint_col_18) is not null and decimal2709_col_9 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: decimal2709_col_9 (type: decimal(27,9)), UDFToLong(tinyint_col_18) (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: bigint), _col0 (type: decimal(27,9)) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: bigint), _col0 (type: decimal(27,9)) + Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: tt1 + filterExpr: (decimal1309_col_65 is not null and timestamp_col_66 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (decimal1309_col_65 is not null and timestamp_col_66 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: decimal1309_col_65 (type: decimal(13,9)), timestamp_col_66 (type: timestamp) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: decimal(19,11)), _col1 (type: timestamp) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(19,11)), _col1 (type: timestamp) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 8 + Map Operator Tree: + TableScan + alias: tt2 + filterExpr: (decimal1911_col_16 is not null and timestamp_col_19 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (decimal1911_col_16 is not null and timestamp_col_19 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_19 (type: timestamp) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: decimal(19,11)), _col1 (type: timestamp) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(19,11)), _col1 (type: timestamp) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: bigint), _col1 (type: decimal(27,9)) + 1 _col1 (type: bigint), _col0 (type: decimal(27,9)) + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + Statistics: Num rows: 1 Data size: 304 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 498 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 304 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 304 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: decimal(19,11)), _col1 (type: timestamp) + 1 _col0 (type: decimal(19,11)), _col1 (type: timestamp) + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: true (type: boolean) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: boolean) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: boolean) + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Reducer 7 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: boolean) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/semijoin5.q.out ql/src/test/results/clientpositive/llap/semijoin5.q.out similarity index 50% rename from ql/src/test/results/clientpositive/semijoin5.q.out rename to ql/src/test/results/clientpositive/llap/semijoin5.q.out index bacf59adf1..2530769af8 100644 --- ql/src/test/results/clientpositive/semijoin5.q.out +++ ql/src/test/results/clientpositive/llap/semijoin5.q.out @@ -54,213 +54,207 @@ POSTHOOK: Input: default@table_1_n1 #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-3 depends on stages: Stage-2 - Stage-5 is a root stage - Stage-0 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: (bigint_col_7 is not null and decimal2016_col_26 is not null and tinyint_col_3 is not null and timestamp_col_9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (bigint_col_7 is not null and decimal2016_col_26 is not null and tinyint_col_3 is not null and timestamp_col_9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: tinyint_col_3 (type: tinyint), bigint_col_7 (type: bigint), timestamp_col_9 (type: timestamp), double_col_16 (type: double), decimal2016_col_26 (type: decimal(20,16)), smallint_col_50 (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 7 <- Map 6 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + filterExpr: (bigint_col_7 is not null and decimal2016_col_26 is not null and tinyint_col_3 is not null and timestamp_col_9 is not null) (type: boolean) Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: timestamp), _col3 (type: double), _col5 (type: smallint) - TableScan - alias: t2 - filterExpr: (UDFToLong(tinyint_col_15) is not null and decimal2709_col_9 is not null and tinyint_col_20 is not null and UDFToInteger(smallint_col_19) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToLong(tinyint_col_15) is not null and decimal2709_col_9 is not null and tinyint_col_20 is not null and UDFToInteger(smallint_col_19) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: decimal2709_col_9 (type: decimal(27,9)), int_col_10 (type: int), tinyint_col_15 (type: tinyint), smallint_col_19 (type: smallint), tinyint_col_20 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) + Filter Operator + predicate: (bigint_col_7 is not null and decimal2016_col_26 is not null and tinyint_col_3 is not null and timestamp_col_9 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: tinyint_col_3 (type: tinyint), bigint_col_7 (type: bigint), timestamp_col_9 (type: timestamp), double_col_16 (type: double), decimal2016_col_26 (type: decimal(20,16)), smallint_col_50 (type: smallint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) + Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: timestamp), _col3 (type: double), _col5 (type: smallint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: t2 + filterExpr: (UDFToLong(tinyint_col_15) is not null and decimal2709_col_9 is not null and tinyint_col_20 is not null and UDFToInteger(smallint_col_19) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: smallint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) - 1 _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) - outputColumnNames: _col2, _col3, _col5, _col7, _col9 - Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: timestamp), UDFToInteger(_col9) (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col2 (type: timestamp), UDFToInteger(_col9) (type: int) - Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: double), _col5 (type: smallint), _col7 (type: int) - TableScan - Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: int) - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col2 (type: timestamp), UDFToInteger(_col9) (type: int) - 1 _col0 (type: timestamp), _col1 (type: int) - outputColumnNames: _col3, _col5, _col7 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: (_col7 + UDFToInteger(_col5)) (type: int), floor(_col3) (type: bigint) - null sort order: zz - sort order: -- - Map-reduce partition columns: (_col7 + UDFToInteger(_col5)) (type: int) - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: double), _col5 (type: smallint), _col7 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col3 (type: double), VALUE._col5 (type: smallint), VALUE._col7 (type: int) - outputColumnNames: _col3, _col5, _col7 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col3: double, _col5: smallint, _col7: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (_col7 + UDFToInteger(_col5)) DESC NULLS LAST, floor(_col3) DESC NULLS LAST - partition by: (_col7 + UDFToInteger(_col5)) - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: 62 - name: sum - window function: GenericUDAFSumLong - window frame: ROWS PRECEDING(MAX)~FOLLOWING(48) - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 498 (type: int), (_col7 + UDFToInteger(_col5)) (type: int), floor(_col3) (type: bigint), CASE WHEN (sum_window_0 is not null) THEN (sum_window_0) ELSE (704L) END (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Filter Operator + predicate: (UDFToLong(tinyint_col_15) is not null and decimal2709_col_9 is not null and tinyint_col_20 is not null and UDFToInteger(smallint_col_19) is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: decimal2709_col_9 (type: decimal(27,9)), int_col_10 (type: int), tinyint_col_15 (type: tinyint), smallint_col_19 (type: smallint), tinyint_col_20 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) + null sort order: zzz + sort order: +++ + Map-reduce partition columns: _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) + Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: smallint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 6 + Map Operator Tree: + TableScan + alias: tt2 + filterExpr: (timestamp_col_18 is not null and decimal1911_col_16 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (timestamp_col_18 is not null and decimal1911_col_16 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_18 (type: timestamp) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: decimal(26,12)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(26,12)) + Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: timestamp) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 8 + Map Operator Tree: + TableScan + alias: tt1 + filterExpr: decimal2612_col_77 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: decimal2612_col_77 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: decimal2612_col_77 (type: decimal(26,12)) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: decimal(26,12)) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: decimal(26,12)) + Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: tinyint), _col4 (type: decimal(34,16)), _col1 (type: bigint) + 1 _col4 (type: tinyint), _col0 (type: decimal(34,16)), UDFToLong(_col2) (type: bigint) + outputColumnNames: _col2, _col3, _col5, _col7, _col9 + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: timestamp), UDFToInteger(_col9) (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col2 (type: timestamp), UDFToInteger(_col9) (type: int) + Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: double), _col5 (type: smallint), _col7 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col2 (type: timestamp), UDFToInteger(_col9) (type: int) + 1 _col0 (type: timestamp), _col1 (type: int) + outputColumnNames: _col3, _col5, _col7 Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: tt2 - filterExpr: (timestamp_col_18 is not null and decimal1911_col_16 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (timestamp_col_18 is not null and decimal1911_col_16 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_18 (type: timestamp) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: decimal(26,12)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(26,12)) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: timestamp) - TableScan - alias: tt1 - filterExpr: decimal2612_col_77 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: decimal2612_col_77 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE + key expressions: (_col7 + UDFToInteger(_col5)) (type: int), floor(_col3) (type: bigint) + null sort order: zz + sort order: -- + Map-reduce partition columns: (_col7 + UDFToInteger(_col5)) (type: int) + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: double), _col5 (type: smallint), _col7 (type: int) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: Select Operator - expressions: decimal2612_col_77 (type: decimal(26,12)) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: decimal(26,12)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(26,12)) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: decimal(26,12)) - 1 _col0 (type: decimal(26,12)) - outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: timestamp), -92 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: timestamp), _col1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + expressions: VALUE._col3 (type: double), VALUE._col5 (type: smallint), VALUE._col7 (type: int) + outputColumnNames: _col3, _col5, _col7 + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col3: double, _col5: smallint, _col7: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: (_col7 + UDFToInteger(_col5)) DESC NULLS LAST, floor(_col3) DESC NULLS LAST + partition by: (_col7 + UDFToInteger(_col5)) + raw input shape: + window functions: + window function definition + alias: sum_window_0 + arguments: 62 + name: sum + window function: GenericUDAFSumLong + window frame: ROWS PRECEDING(MAX)~FOLLOWING(48) + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 498 (type: int), (_col7 + UDFToInteger(_col5)) (type: int), floor(_col3) (type: bigint), CASE WHEN (sum_window_0 is not null) THEN (sum_window_0) ELSE (704L) END (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: decimal(26,12)) + 1 _col0 (type: decimal(26,12)) + outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: timestamp), -92 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: timestamp), _col1 (type: int) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: timestamp), _col1 (type: int) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: int) + Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/serde_multi_delimit.q.out ql/src/test/results/clientpositive/llap/serde_multi_delimit.q.out similarity index 98% rename from ql/src/test/results/clientpositive/serde_multi_delimit.q.out rename to ql/src/test/results/clientpositive/llap/serde_multi_delimit.q.out index f13aa59d5a..34377448d8 100644 --- ql/src/test/results/clientpositive/serde_multi_delimit.q.out +++ ql/src/test/results/clientpositive/llap/serde_multi_delimit.q.out @@ -90,7 +90,7 @@ NULL NULL NULL NULL NULL 8 8 8 8 9 9 9 9 10101010 NULL NULL NULL NULL -Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: SELECT EXISTS ( SELECT colA, colB, colC, colD, colE FROM t1_multi_delimit MINUS diff --git ql/src/test/results/clientpositive/llap/set_processor_namespaces.q.out ql/src/test/results/clientpositive/llap/set_processor_namespaces.q.out new file mode 100644 index 0000000000..040680c80b --- /dev/null +++ ql/src/test/results/clientpositive/llap/set_processor_namespaces.q.out @@ -0,0 +1,45 @@ +zzz=5 +system:xxx=5 +system:yyy=5 +go=5 +raw=${hiveconf:zzz} +PREHOOK: query: EXPLAIN SELECT * FROM src where key=5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src where key=5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) = 5.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(key) = 5.0D) (type: boolean) + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: SELECT * FROM src where key=5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM src where key=5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +5 val_5 +5 val_5 +5 val_5 +c=1 +x=1 +x=2 diff --git ql/src/test/results/clientpositive/llap/set_variable_sub.q.out ql/src/test/results/clientpositive/llap/set_variable_sub.q.out new file mode 100644 index 0000000000..9893872e18 --- /dev/null +++ ql/src/test/results/clientpositive/llap/set_variable_sub.q.out @@ -0,0 +1,82 @@ +PREHOOK: query: EXPLAIN SELECT * FROM src where key="value1" +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src where key="value1" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (key = 'value1') (type: boolean) + Filter Operator + predicate: (key = 'value1') (type: boolean) + Select Operator + expressions: 'value1' (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: EXPLAIN SELECT * FROM src where key="value1" +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src where key="value1" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (key = 'value1') (type: boolean) + Filter Operator + predicate: (key = 'value1') (type: boolean) + Select Operator + expressions: 'value1' (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +PREHOOK: query: EXPLAIN SELECT * FROM src where key="1" +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN SELECT * FROM src where key="1" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + filterExpr: (key = '1') (type: boolean) + Filter Operator + predicate: (key = '1') (type: boolean) + Select Operator + expressions: '1' (type: string), value (type: string) + outputColumnNames: _col0, _col1 + ListSink + +hivevar:a=1 +hivevar:b=a +hivevar:c=1 +hivevar:key1=value1 diff --git ql/src/test/results/clientpositive/setop_no_distinct.q.out ql/src/test/results/clientpositive/llap/setop_no_distinct.q.out similarity index 100% rename from ql/src/test/results/clientpositive/setop_no_distinct.q.out rename to ql/src/test/results/clientpositive/llap/setop_no_distinct.q.out diff --git ql/src/test/results/clientpositive/llap/setop_subq.q.out ql/src/test/results/clientpositive/llap/setop_subq.q.out new file mode 100644 index 0000000000..0e2c05b510 --- /dev/null +++ ql/src/test/results/clientpositive/llap/setop_subq.q.out @@ -0,0 +1,631 @@ +PREHOOK: query: explain select key from ((select key from src) union (select key from src))subq +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select key from ((select key from src) union (select key from src))subq +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Union 2 (CONTAINS) + Map 4 <- Union 2 (CONTAINS) + Reducer 3 <- Union 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.684 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.684 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union 2 + Vertex: Union 2 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select key from ((select key from src) intersect (select key from src))subq +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select key from ((select key from src) intersect (select key from src))subq +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 4 <- Union 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 = 2L) (type: boolean) + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Union 3 + Vertex: Union 3 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select key from ((select key from src) intersect select key from src)subq +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select key from ((select key from src) intersect select key from src)subq +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 4 <- Union 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 = 2L) (type: boolean) + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Union 3 + Vertex: Union 3 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select key from (select key from src intersect (select key from src))subq +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select key from (select key from src intersect (select key from src))subq +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 4 <- Union 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col1 = 2L) (type: boolean) + Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Union 3 + Vertex: Union 3 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select a.key, b.value from ( (select key from src)a join (select value from src)b on a.key=b.value) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select a.key, b.value from ( (select key from src)a join (select value from src)b on a.key=b.value) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/show_create_table_db_table.q.out ql/src/test/results/clientpositive/llap/show_create_table_db_table.q.out similarity index 100% rename from ql/src/test/results/clientpositive/show_create_table_db_table.q.out rename to ql/src/test/results/clientpositive/llap/show_create_table_db_table.q.out diff --git ql/src/test/results/clientpositive/show_create_table_delimited.q.out ql/src/test/results/clientpositive/llap/show_create_table_delimited.q.out similarity index 100% rename from ql/src/test/results/clientpositive/show_create_table_delimited.q.out rename to ql/src/test/results/clientpositive/llap/show_create_table_delimited.q.out diff --git ql/src/test/results/clientpositive/show_create_table_temp_table.q.out ql/src/test/results/clientpositive/llap/show_create_table_temp_table.q.out similarity index 100% rename from ql/src/test/results/clientpositive/show_create_table_temp_table.q.out rename to ql/src/test/results/clientpositive/llap/show_create_table_temp_table.q.out diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin1.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin1.q.out new file mode 100644 index 0000000000..69d765471e --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin1.q.out @@ -0,0 +1,464 @@ +PREHOOK: query: CREATE TABLE T1_n67(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n67 +POSTHOOK: query: CREATE TABLE T1_n67(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n67 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n67 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n67 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n67 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n67 +PREHOOK: query: CREATE TABLE T2_n40(key STRING, val STRING) +SKEWED BY (key) ON ((3)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n40 +POSTHOOK: query: CREATE TABLE T2_n40(key STRING, val STRING) +SKEWED BY (key) ON ((3)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n40 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n40 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n40 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n40 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n40 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 2 <- Map 1 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 0 Map 1 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +NULL NULL 4 14 +NULL NULL 5 15 +PREHOOK: query: EXPLAIN +SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 3 + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +6 +PREHOOK: query: EXPLAIN +SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 0 Map 1 + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n67 +PREHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +POSTHOOK: query: SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n67 +POSTHOOK: Input: default@t2_n40 +#### A masked pattern was here #### +8 diff --git ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin10.q.out similarity index 57% rename from ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out rename to ql/src/test/results/clientpositive/llap/skewjoin_mapjoin10.q.out index 2288d79244..3c433ea3e7 100644 --- ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin10.q.out @@ -1,82 +1,82 @@ -PREHOOK: query: CREATE TABLE tmpT1_n109(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE tmpT1_n0(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default -PREHOOK: Output: default@tmpT1_n109 -POSTHOOK: query: CREATE TABLE tmpT1_n109(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: Output: default@tmpT1_n0 +POSTHOOK: query: CREATE TABLE tmpT1_n0(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmpT1_n109 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1_n109 +POSTHOOK: Output: default@tmpT1_n0 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1_n0 PREHOOK: type: LOAD #### A masked pattern was here #### -PREHOOK: Output: default@tmpt1_n109 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1_n109 +PREHOOK: Output: default@tmpt1_n0 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1_n0 POSTHOOK: type: LOAD #### A masked pattern was here #### -POSTHOOK: Output: default@tmpt1_n109 -PREHOOK: query: CREATE TABLE T1_n109(key INT, val STRING) SKEWED BY (key) ON ((2)) +POSTHOOK: Output: default@tmpt1_n0 +PREHOOK: query: CREATE TABLE T1_n151(key INT, val STRING) SKEWED BY (key) ON ((2)) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n109 -POSTHOOK: query: CREATE TABLE T1_n109(key INT, val STRING) SKEWED BY (key) ON ((2)) +PREHOOK: Output: default@T1_n151 +POSTHOOK: query: CREATE TABLE T1_n151(key INT, val STRING) SKEWED BY (key) ON ((2)) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n109 -PREHOOK: query: INSERT OVERWRITE TABLE T1_n109 SELECT key, val FROM tmpT1_n109 +POSTHOOK: Output: default@T1_n151 +PREHOOK: query: INSERT OVERWRITE TABLE T1_n151 SELECT key, val FROM tmpT1_n0 PREHOOK: type: QUERY -PREHOOK: Input: default@tmpt1_n109 -PREHOOK: Output: default@t1_n109 -POSTHOOK: query: INSERT OVERWRITE TABLE T1_n109 SELECT key, val FROM tmpT1_n109 +PREHOOK: Input: default@tmpt1_n0 +PREHOOK: Output: default@t1_n151 +POSTHOOK: query: INSERT OVERWRITE TABLE T1_n151 SELECT key, val FROM tmpT1_n0 POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmpt1_n109 -POSTHOOK: Output: default@t1_n109 -POSTHOOK: Lineage: t1_n109.key EXPRESSION [(tmpt1_n109)tmpt1_n109.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: t1_n109.val SIMPLE [(tmpt1_n109)tmpt1_n109.FieldSchema(name:val, type:string, comment:null), ] -PREHOOK: query: CREATE TABLE tmpT2_n66(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: Input: default@tmpt1_n0 +POSTHOOK: Output: default@t1_n151 +POSTHOOK: Lineage: t1_n151.key EXPRESSION [(tmpt1_n0)tmpt1_n0.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: t1_n151.val SIMPLE [(tmpt1_n0)tmpt1_n0.FieldSchema(name:val, type:string, comment:null), ] +PREHOOK: query: CREATE TABLE tmpT2_n0(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default -PREHOOK: Output: default@tmpT2_n66 -POSTHOOK: query: CREATE TABLE tmpT2_n66(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: Output: default@tmpT2_n0 +POSTHOOK: query: CREATE TABLE tmpT2_n0(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmpT2_n66 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2_n66 +POSTHOOK: Output: default@tmpT2_n0 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2_n0 PREHOOK: type: LOAD #### A masked pattern was here #### -PREHOOK: Output: default@tmpt2_n66 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2_n66 +PREHOOK: Output: default@tmpt2_n0 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2_n0 POSTHOOK: type: LOAD #### A masked pattern was here #### -POSTHOOK: Output: default@tmpt2_n66 -PREHOOK: query: CREATE TABLE T2_n66(key INT, val STRING) SKEWED BY (key) ON ((3)) +POSTHOOK: Output: default@tmpt2_n0 +PREHOOK: query: CREATE TABLE T2_n88(key INT, val STRING) SKEWED BY (key) ON ((3)) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n66 -POSTHOOK: query: CREATE TABLE T2_n66(key INT, val STRING) SKEWED BY (key) ON ((3)) +PREHOOK: Output: default@T2_n88 +POSTHOOK: query: CREATE TABLE T2_n88(key INT, val STRING) SKEWED BY (key) ON ((3)) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n66 -PREHOOK: query: INSERT OVERWRITE TABLE T2_n66 SELECT key, val FROM tmpT2_n66 +POSTHOOK: Output: default@T2_n88 +PREHOOK: query: INSERT OVERWRITE TABLE T2_n88 SELECT key, val FROM tmpT2_n0 PREHOOK: type: QUERY -PREHOOK: Input: default@tmpt2_n66 -PREHOOK: Output: default@t2_n66 -POSTHOOK: query: INSERT OVERWRITE TABLE T2_n66 SELECT key, val FROM tmpT2_n66 +PREHOOK: Input: default@tmpt2_n0 +PREHOOK: Output: default@t2_n88 +POSTHOOK: query: INSERT OVERWRITE TABLE T2_n88 SELECT key, val FROM tmpT2_n0 POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmpt2_n66 -POSTHOOK: Output: default@t2_n66 -POSTHOOK: Lineage: t2_n66.key EXPRESSION [(tmpt2_n66)tmpt2_n66.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: t2_n66.val SIMPLE [(tmpt2_n66)tmpt2_n66.FieldSchema(name:val, type:string, comment:null), ] +POSTHOOK: Input: default@tmpt2_n0 +POSTHOOK: Output: default@t2_n88 +POSTHOOK: Lineage: t2_n88.key EXPRESSION [(tmpt2_n0)tmpt2_n0.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: t2_n88.val SIMPLE [(tmpt2_n0)tmpt2_n0.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage @@ -87,7 +87,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Map 1 <- Map 2 (BROADCAST_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -103,16 +103,26 @@ STAGE PLANS: expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: no inputs - Map 3 + Map 2 Map Operator Tree: TableScan alias: b @@ -134,24 +144,6 @@ STAGE PLANS: value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -159,17 +151,17 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: SELECT a.*, b.* FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +PREHOOK: query: SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key ORDER BY a.key, b.key, a.val, b.val PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +POSTHOOK: query: SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key ORDER BY a.key, b.key, a.val, b.val POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### 2 12 2 22 3 13 3 13 @@ -178,16 +170,16 @@ POSTHOOK: Input: default@t2_n66 8 28 8 18 8 28 8 18 PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage @@ -198,7 +190,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Map 2 <- Map 1 (BROADCAST_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -223,7 +215,7 @@ STAGE PLANS: value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs - Map 3 + Map 2 Map Operator Tree: TableScan alias: b @@ -232,33 +224,25 @@ STAGE PLANS: expressions: key (type: int), val (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + Map Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 0 Map 1 + Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 1260 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -266,17 +250,17 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: SELECT a.*, b.* FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +PREHOOK: query: SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key ORDER BY a.key, b.key, a.val, b.val PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +POSTHOOK: query: SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key ORDER BY a.key, b.key, a.val, b.val POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### 2 12 2 22 3 13 3 13 @@ -287,16 +271,16 @@ POSTHOOK: Input: default@t2_n66 NULL NULL 4 14 NULL NULL 5 15 PREHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### POSTHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage @@ -307,8 +291,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -324,15 +308,29 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.85714287 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs - Map 4 + Map 3 Map Operator Tree: TableScan alias: b @@ -354,27 +352,6 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.85714287 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -396,28 +373,28 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: SELECT count(1) FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +PREHOOK: query: SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### -POSTHOOK: query: SELECT count(1) FROM T1_n109 a JOIN T2_n66 b ON a.key = b.key +POSTHOOK: query: SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### 6 PREHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### POSTHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage @@ -428,8 +405,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -453,7 +430,7 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs - Map 4 + Map 2 Map Operator Tree: TableScan alias: b @@ -462,35 +439,28 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 0 Map 1 + Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.85714287 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.85714287 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: @@ -513,14 +483,14 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: SELECT count(1) FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +PREHOOK: query: SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n109 -PREHOOK: Input: default@t2_n66 +PREHOOK: Input: default@t1_n151 +PREHOOK: Input: default@t2_n88 #### A masked pattern was here #### -POSTHOOK: query: SELECT count(1) FROM T1_n109 a RIGHT OUTER JOIN T2_n66 b ON a.key = b.key +POSTHOOK: query: SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n109 -POSTHOOK: Input: default@t2_n66 +POSTHOOK: Input: default@t1_n151 +POSTHOOK: Input: default@t2_n88 #### A masked pattern was here #### 8 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin11.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin11.q.out new file mode 100644 index 0000000000..8114297f7b --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin11.q.out @@ -0,0 +1,134 @@ +PREHOOK: query: CREATE TABLE T1_n31(key STRING, val STRING) +CLUSTERED BY (key) INTO 4 BUCKETS +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n31 +POSTHOOK: query: CREATE TABLE T1_n31(key STRING, val STRING) +CLUSTERED BY (key) INTO 4 BUCKETS +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n31 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/bucket_files/000000_0' INTO TABLE T1_n31 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n31 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/bucket_files/000000_0' INTO TABLE T1_n31 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n31 +PREHOOK: query: CREATE TABLE T2_n21(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n21 +POSTHOOK: query: CREATE TABLE T2_n21(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n21 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n21 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n21 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n21 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n21 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n31 +PREHOOK: Input: default@t2_n21 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n31 +POSTHOOK: Input: default@t2_n21 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (CUSTOM_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n31 +PREHOOK: Input: default@t2_n21 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n31 +POSTHOOK: Input: default@t2_n21 +#### A masked pattern was here #### +3 13 3 13 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin2.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin2.q.out new file mode 100644 index 0000000000..6cfdf6540e --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin2.q.out @@ -0,0 +1,246 @@ +PREHOOK: query: CREATE TABLE T1_n25(key STRING, val STRING) +SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n25 +POSTHOOK: query: CREATE TABLE T1_n25(key STRING, val STRING) +SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n25 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n25 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n25 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n25 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n25 +PREHOOK: query: CREATE TABLE T2_n16(key STRING, val STRING) +SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n16 +POSTHOOK: query: CREATE TABLE T2_n16(key STRING, val STRING) +SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n16 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n16 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n16 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n16 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n16 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n25 +PREHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n25 +POSTHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n25 +PREHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n25 +POSTHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n25 +PREHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n25 +POSTHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n25 +PREHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n25 +POSTHOOK: Input: default@t2_n16 +#### A masked pattern was here #### +1 11 NULL NULL +2 12 2 22 +3 13 3 13 +7 17 NULL NULL +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +NULL NULL 4 14 +NULL NULL 5 15 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin3.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin3.q.out new file mode 100644 index 0000000000..dc8274ce53 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin3.q.out @@ -0,0 +1,139 @@ +PREHOOK: query: CREATE TABLE T1_n155(key STRING, val STRING) +SKEWED BY (key, val) ON ((2, 12), (8, 18)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n155 +POSTHOOK: query: CREATE TABLE T1_n155(key STRING, val STRING) +SKEWED BY (key, val) ON ((2, 12), (8, 18)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n155 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n155 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n155 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n155 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n155 +PREHOOK: query: CREATE TABLE T2_n91(key STRING, val STRING) +SKEWED BY (key, val) ON ((3, 13), (8, 18)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n91 +POSTHOOK: query: CREATE TABLE T2_n91(key STRING, val STRING) +SKEWED BY (key, val) ON ((3, 13), (8, 18)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n91 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n91 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n91 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n91 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n91 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n155 +PREHOOK: Input: default@t2_n91 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n155 +POSTHOOK: Input: default@t2_n91 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n155 +PREHOOK: Input: default@t2_n91 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n155 +POSTHOOK: Input: default@t2_n91 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin4.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin4.q.out new file mode 100644 index 0000000000..8f25e990b4 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin4.q.out @@ -0,0 +1,186 @@ +PREHOOK: query: CREATE TABLE T1_n124(key STRING, val STRING) +SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n124 +POSTHOOK: query: CREATE TABLE T1_n124(key STRING, val STRING) +SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n124 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n124 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n124 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n124 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n124 +PREHOOK: query: CREATE TABLE T2_n73(key STRING, val STRING) +SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n73 +POSTHOOK: query: CREATE TABLE T2_n73(key STRING, val STRING) +SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n73 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n73 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n73 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n73 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n73 +PREHOOK: query: CREATE TABLE T3_n27(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T3_n27 +POSTHOOK: query: CREATE TABLE T3_n27(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T3_n27 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n27 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t3_n27 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n27 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t3_n27 +PREHOOK: query: EXPLAIN +SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n124 +PREHOOK: Input: default@t2_n73 +PREHOOK: Input: default@t3_n27 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n124 +POSTHOOK: Input: default@t2_n73 +POSTHOOK: Input: default@t3_n27 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 3 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: c + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key +ORDER BY a.key, b.key, c.key, a.val, b.val, c.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n124 +PREHOOK: Input: default@t2_n73 +PREHOOK: Input: default@t3_n27 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key +ORDER BY a.key, b.key, c.key, a.val, b.val, c.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n124 +POSTHOOK: Input: default@t2_n73 +POSTHOOK: Input: default@t3_n27 +#### A masked pattern was here #### +2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin5.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin5.q.out new file mode 100644 index 0000000000..cc09233f2b --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin5.q.out @@ -0,0 +1,345 @@ +PREHOOK: query: CREATE TABLE T1_n87(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n87 +POSTHOOK: query: CREATE TABLE T1_n87(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n87 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n87 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n87 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n87 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n87 +PREHOOK: query: CREATE TABLE T2_n54(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n54 +POSTHOOK: query: CREATE TABLE T2_n54(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n54 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n54 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n54 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n54 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n54 +PREHOOK: query: EXPLAIN +select * from +( +select key, val from T1_n87 + union all +select key, val from T1_n87 +) subq1 +join T2_n54 b on subq1.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n87 +PREHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +select * from +( +select key, val from T1_n87 + union all +select key, val from T1_n87 +) subq1 +join T2_n54 b on subq1.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n87 +POSTHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 4 (BROADCAST_EDGE), Union 2 (CONTAINS) + Map 3 <- Map 4 (BROADCAST_EDGE), Union 2 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n87 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 4 + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: t1_n87 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 4 + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Union 2 + Vertex: Union 2 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from +( +select key, val from T1_n87 + union all +select key, val from T1_n87 +) subq1 +join T2_n54 b on subq1.key = b.key +ORDER BY subq1.key, b.key, subq1.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n87 +PREHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +POSTHOOK: query: select * from +( +select key, val from T1_n87 + union all +select key, val from T1_n87 +) subq1 +join T2_n54 b on subq1.key = b.key +ORDER BY subq1.key, b.key, subq1.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n87 +POSTHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +2 12 2 22 +2 12 2 22 +3 13 3 13 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: EXPLAIN +select * from +( +select key, count(1) as cnt from T1_n87 group by key +) subq1 +join T2_n54 b on subq1.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n87 +PREHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +select * from +( +select key, count(1) as cnt from T1_n87 group by key +) subq1 +join T2_n54 b on subq1.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n87 +POSTHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n87 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 3 + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from +( +select key, count(1) as cnt from T1_n87 group by key +) subq1 +join T2_n54 b on subq1.key = b.key +ORDER BY subq1.key, b.key, subq1.cnt, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n87 +PREHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +POSTHOOK: query: select * from +( +select key, count(1) as cnt from T1_n87 group by key +) subq1 +join T2_n54 b on subq1.key = b.key +ORDER BY subq1.key, b.key, subq1.cnt, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n87 +POSTHOOK: Input: default@t2_n54 +#### A masked pattern was here #### +2 1 2 22 +3 1 3 13 +8 2 8 18 +8 2 8 18 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin6.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin6.q.out new file mode 100644 index 0000000000..3eea8ad1fc --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin6.q.out @@ -0,0 +1,164 @@ +PREHOOK: query: CREATE TABLE T1_n39(key STRING, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n39 +POSTHOOK: query: CREATE TABLE T1_n39(key STRING, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n39 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n39 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n39 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n39 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n39 +PREHOOK: query: drop table array_valued_T1_n39 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table array_valued_T1_n39 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table array_valued_T1_n39 (key string, value array) SKEWED BY (key) ON ((8)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@array_valued_T1_n39 +POSTHOOK: query: create table array_valued_T1_n39 (key string, value array) SKEWED BY (key) ON ((8)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@array_valued_T1_n39 +PREHOOK: query: insert overwrite table array_valued_T1_n39 select key, array(value) from T1_n39 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n39 +PREHOOK: Output: default@array_valued_t1_n39 +POSTHOOK: query: insert overwrite table array_valued_T1_n39 select key, array(value) from T1_n39 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n39 +POSTHOOK: Output: default@array_valued_t1_n39 +POSTHOOK: Lineage: array_valued_t1_n39.key SIMPLE [(t1_n39)t1_n39.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: array_valued_t1_n39.value EXPRESSION [(t1_n39)t1_n39.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain +select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val +PREHOOK: type: QUERY +PREHOOK: Input: default@array_valued_t1_n39 +PREHOOK: Input: default@t1_n39 +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@array_valued_t1_n39 +POSTHOOK: Input: default@t1_n39 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 2 <- Map 1 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: string) + 1 key (type: string) + outputColumnNames: _col0, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col6 (type: array) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: array) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 27772 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 27772 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: _col1 (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE + function name: explode + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 27772 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 27772 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val +ORDER BY key, val +PREHOOK: type: QUERY +PREHOOK: Input: default@array_valued_t1_n39 +PREHOOK: Input: default@t1_n39 +#### A masked pattern was here #### +POSTHOOK: query: select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val +ORDER BY key, val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@array_valued_t1_n39 +POSTHOOK: Input: default@t1_n39 +#### A masked pattern was here #### +1 ["11"] 11 +2 ["12"] 12 +3 ["13"] 13 +7 ["17"] 17 +8 ["18"] 18 +8 ["18"] 18 +8 ["28"] 28 +8 ["28"] 28 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin7.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin7.q.out new file mode 100644 index 0000000000..6b1439c2b8 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin7.q.out @@ -0,0 +1,228 @@ +PREHOOK: query: CREATE TABLE T1_n157(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n157 +POSTHOOK: query: CREATE TABLE T1_n157(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n157 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n157 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n157 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n157 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n157 +PREHOOK: query: CREATE TABLE T2_n92(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n92 +POSTHOOK: query: CREATE TABLE T2_n92(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n92 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n92 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n92 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n92 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n92 +PREHOOK: query: EXPLAIN +select * from +( + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key +) subq1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n157 +PREHOOK: Input: default@t2_n92 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +select * from +( + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key +) subq1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n157 +POSTHOOK: Input: default@t2_n92 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE), Union 2 (CONTAINS) + Map 4 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 1 Map 3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 1 Map 5 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Union 2 + Vertex: Union 2 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from +( + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key +) subq1 +ORDER BY key, val1, val2 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n157 +PREHOOK: Input: default@t2_n92 +#### A masked pattern was here #### +POSTHOOK: query: select * from +( + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key + union all + select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key +) subq1 +ORDER BY key, val1, val2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n157 +POSTHOOK: Input: default@t2_n92 +#### A masked pattern was here #### +2 12 22 +2 12 22 +3 13 13 +3 13 13 +8 18 18 +8 18 18 +8 18 18 +8 18 18 +8 28 18 +8 28 18 +8 28 18 +8 28 18 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin8.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin8.q.out new file mode 100644 index 0000000000..0a99863484 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin8.q.out @@ -0,0 +1,196 @@ +PREHOOK: query: CREATE TABLE T1_n29(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n29 +POSTHOOK: query: CREATE TABLE T1_n29(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n29 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n29 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n29 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n29 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n29 +PREHOOK: query: CREATE TABLE T2_n20(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n20 +POSTHOOK: query: CREATE TABLE T2_n20(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n20 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n20 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n20 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n20 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n20 +PREHOOK: query: CREATE TABLE T3_n7(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T3_n7 +POSTHOOK: query: CREATE TABLE T3_n7(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T3_n7 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n7 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t3_n7 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n7 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t3_n7 +PREHOOK: query: EXPLAIN +select * +from +T1_n29 a join T2_n20 b on a.key = b.key +join T3_n7 c on a.val = c.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n29 +PREHOOK: Input: default@t2_n20 +PREHOOK: Input: default@t3_n7 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +select * +from +T1_n29 a join T2_n20 b on a.key = b.key +join T3_n7 c on a.val = c.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n29 +POSTHOOK: Input: default@t2_n20 +POSTHOOK: Input: default@t3_n7 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (key is not null and val is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and val is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 3 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: c + filterExpr: val is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: val is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * +from +T1_n29 a join T2_n20 b on a.key = b.key +join T3_n7 c on a.val = c.val +order by a.key, b.key, c.key, a.val, b.val, c.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n29 +PREHOOK: Input: default@t2_n20 +PREHOOK: Input: default@t3_n7 +#### A masked pattern was here #### +POSTHOOK: query: select * +from +T1_n29 a join T2_n20 b on a.key = b.key +join T3_n7 c on a.val = c.val +order by a.key, b.key, c.key, a.val, b.val, c.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n29 +POSTHOOK: Input: default@t2_n20 +POSTHOOK: Input: default@t3_n7 +#### A masked pattern was here #### +2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/llap/skewjoin_mapjoin9.q.out ql/src/test/results/clientpositive/llap/skewjoin_mapjoin9.q.out new file mode 100644 index 0000000000..f9d39b41cf --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_mapjoin9.q.out @@ -0,0 +1,198 @@ +PREHOOK: query: CREATE TABLE T1_n152(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n152 +POSTHOOK: query: CREATE TABLE T1_n152(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n152 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n152 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n152 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n152 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n152 +PREHOOK: query: CREATE TABLE T2_n89(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n89 +POSTHOOK: query: CREATE TABLE T2_n89(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n89 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n89 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n89 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n89 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n89 +PREHOOK: query: CREATE TABLE T3_n36(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T3_n36 +POSTHOOK: query: CREATE TABLE T3_n36(key STRING, val STRING) +SKEWED BY (val) ON ((12)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T3_n36 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n36 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t3_n36 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n36 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t3_n36 +PREHOOK: query: EXPLAIN +select * +from +T1_n152 a join T2_n89 b on a.key = b.key +join T3_n36 c on a.val = c.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n152 +PREHOOK: Input: default@t2_n89 +PREHOOK: Input: default@t3_n36 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +select * +from +T1_n152 a join T2_n89 b on a.key = b.key +join T3_n36 c on a.val = c.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n152 +POSTHOOK: Input: default@t2_n89 +POSTHOOK: Input: default@t3_n36 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: (key is not null and val is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and val is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Map 2 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 3 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: c + filterExpr: val is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: val is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * +from +T1_n152 a join T2_n89 b on a.key = b.key +join T3_n36 c on a.val = c.val +order by a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n152 +PREHOOK: Input: default@t2_n89 +PREHOOK: Input: default@t3_n36 +#### A masked pattern was here #### +POSTHOOK: query: select * +from +T1_n152 a join T2_n89 b on a.key = b.key +join T3_n36 c on a.val = c.val +order by a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n152 +POSTHOOK: Input: default@t2_n89 +POSTHOOK: Input: default@t3_n36 +#### A masked pattern was here #### +2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/llap/skewjoin_noskew.q.out ql/src/test/results/clientpositive/llap/skewjoin_noskew.q.out new file mode 100644 index 0000000000..8929b61d53 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_noskew.q.out @@ -0,0 +1,220 @@ +PREHOOK: query: explain +create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@noskew +POSTHOOK: query: explain +create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@noskew +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-4 depends on stages: Stage-0, Stage-2 + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: + + keys: _col0 (type: string) + null sort order: z + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + top n: 30 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 30 + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.noskew + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: col1, col2 + Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll') + minReductionHashAggr: 0.96666664 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-4 + Create Table + columns: key string, value string + name: default.noskew + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.noskew + + Stage: Stage-0 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@noskew +POSTHOOK: query: create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@noskew +POSTHOOK: Lineage: noskew.key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: noskew.value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: select * from noskew +PREHOOK: type: QUERY +PREHOOK: Input: default@noskew +#### A masked pattern was here #### +POSTHOOK: query: select * from noskew +POSTHOOK: type: QUERY +POSTHOOK: Input: default@noskew +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +10 val_10 +100 val_100 +100 val_100 +100 val_100 +100 val_100 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +104 val_104 +104 val_104 +104 val_104 +104 val_104 +105 val_105 +11 val_11 +111 val_111 +113 val_113 +113 val_113 +113 val_113 +113 val_113 +114 val_114 diff --git ql/src/test/results/clientpositive/llap/skewjoin_onesideskew.q.out ql/src/test/results/clientpositive/llap/skewjoin_onesideskew.q.out new file mode 100644 index 0000000000..c25ab387b4 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_onesideskew.q.out @@ -0,0 +1,244 @@ +PREHOOK: query: DROP TABLE IF EXISTS skewtable +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS skewtable +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE skewtable (key STRING, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@skewtable +POSTHOOK: query: CREATE TABLE skewtable (key STRING, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@skewtable +PREHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@skewtable +POSTHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@skewtable +POSTHOOK: Lineage: skewtable.key SCRIPT [] +POSTHOOK: Lineage: skewtable.value SCRIPT [] +PREHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@skewtable +POSTHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@skewtable +POSTHOOK: Lineage: skewtable.key SCRIPT [] +POSTHOOK: Lineage: skewtable.value SCRIPT [] +PREHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@skewtable +POSTHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@skewtable +POSTHOOK: Lineage: skewtable.key SCRIPT [] +POSTHOOK: Lineage: skewtable.value SCRIPT [] +PREHOOK: query: DROP TABLE IF EXISTS nonskewtable +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE IF EXISTS nonskewtable +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE nonskewtable (key STRING, value STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@nonskewtable +POSTHOOK: query: CREATE TABLE nonskewtable (key STRING, value STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@nonskewtable +PREHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("1", "val_1") +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@nonskewtable +POSTHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("1", "val_1") +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@nonskewtable +POSTHOOK: Lineage: nonskewtable.key SCRIPT [] +POSTHOOK: Lineage: nonskewtable.value SCRIPT [] +PREHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("2", "val_2") +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@nonskewtable +POSTHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("2", "val_2") +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@nonskewtable +POSTHOOK: Lineage: nonskewtable.key SCRIPT [] +POSTHOOK: Lineage: nonskewtable.value SCRIPT [] +PREHOOK: query: EXPLAIN +CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@nonskewtable +PREHOOK: Input: default@skewtable +PREHOOK: Output: database:default +PREHOOK: Output: default@result_n1 +POSTHOOK: query: EXPLAIN +CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@nonskewtable +POSTHOOK: Input: default@skewtable +POSTHOOK: Output: database:default +POSTHOOK: Output: default@result_n1 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-4 depends on stages: Stage-0, Stage-2 + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.result_n1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: col1, col2 + Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll') + minReductionHashAggr: 0.6666666 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-4 + Create Table + columns: key string, value string + name: default.result_n1 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat + serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.result_n1 + + Stage: Stage-0 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@nonskewtable +PREHOOK: Input: default@skewtable +PREHOOK: Output: database:default +PREHOOK: Output: default@result_n1 +POSTHOOK: query: CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@nonskewtable +POSTHOOK: Input: default@skewtable +POSTHOOK: Output: database:default +POSTHOOK: Output: default@result_n1 +POSTHOOK: Lineage: result_n1.key SIMPLE [(skewtable)a.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: result_n1.value SIMPLE [(skewtable)a.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: SELECT * FROM result_n1 +PREHOOK: type: QUERY +PREHOOK: Input: default@result_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM result_n1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@result_n1 +#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/llap/skewjoin_union_remove_1.q.out ql/src/test/results/clientpositive/llap/skewjoin_union_remove_1.q.out new file mode 100644 index 0000000000..327cad8746 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_union_remove_1.q.out @@ -0,0 +1,534 @@ +PREHOOK: query: CREATE TABLE T1_n57(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n57 +POSTHOOK: query: CREATE TABLE T1_n57(key STRING, val STRING) +SKEWED BY (key) ON ((2)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n57 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n57 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n57 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n57 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n57 +PREHOOK: query: CREATE TABLE T2_n35(key STRING, val STRING) +SKEWED BY (key) ON ((3)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n35 +POSTHOOK: query: CREATE TABLE T2_n35(key STRING, val STRING) +SKEWED BY (key) ON ((3)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n35 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n35 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n35 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n35 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n35 +PREHOOK: query: EXPLAIN +SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +ORDER BY a.key, b.key, a.val, b.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +NULL NULL 4 14 +NULL NULL 5 15 +PREHOOK: query: create table DEST1_n58(key1 STRING, val1 STRING, key2 STRING, val2 STRING) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@DEST1_n58 +POSTHOOK: query: create table DEST1_n58(key1 STRING, val1 STRING, key2 STRING, val2 STRING) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@DEST1_n58 +PREHOOK: query: EXPLAIN +INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +PREHOOK: Output: default@dest1_n58 +POSTHOOK: query: EXPLAIN +INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +POSTHOOK: Output: default@dest1_n58 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n58 + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n58 + +PREHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +PREHOOK: Output: default@dest1_n58 +POSTHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +POSTHOOK: Output: default@dest1_n58 +POSTHOOK: Lineage: dest1_n58.key1 SIMPLE [(t1_n57)a.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: dest1_n58.key2 SIMPLE [(t2_n35)b.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: dest1_n58.val1 SIMPLE [(t1_n57)a.FieldSchema(name:val, type:string, comment:null), ] +POSTHOOK: Lineage: dest1_n58.val2 SIMPLE [(t2_n35)b.FieldSchema(name:val, type:string, comment:null), ] +PREHOOK: query: SELECT * FROM DEST1_n58 +ORDER BY key1, key2, val1, val2 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1_n58 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM DEST1_n58 +ORDER BY key1, key2, val1, val2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1_n58 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +PREHOOK: query: EXPLAIN +INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +PREHOOK: Output: default@dest1_n58 +POSTHOOK: query: EXPLAIN +INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +POSTHOOK: Output: default@dest1_n58 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n58 + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1_n58 + +PREHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n57 +PREHOOK: Input: default@t2_n35 +PREHOOK: Output: default@dest1_n58 +POSTHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 +SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n57 +POSTHOOK: Input: default@t2_n35 +POSTHOOK: Output: default@dest1_n58 +POSTHOOK: Lineage: dest1_n58.key1 SIMPLE [(t1_n57)a.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: dest1_n58.key2 SIMPLE [(t2_n35)b.FieldSchema(name:key, type:string, comment:null), ] +POSTHOOK: Lineage: dest1_n58.val1 SIMPLE [(t1_n57)a.FieldSchema(name:val, type:string, comment:null), ] +POSTHOOK: Lineage: dest1_n58.val2 SIMPLE [(t2_n35)b.FieldSchema(name:val, type:string, comment:null), ] +PREHOOK: query: SELECT * FROM DEST1_n58 +ORDER BY key1, key2, val1, val2 +PREHOOK: type: QUERY +PREHOOK: Input: default@dest1_n58 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * FROM DEST1_n58 +ORDER BY key1, key2, val1, val2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@dest1_n58 +#### A masked pattern was here #### +2 12 2 22 +3 13 3 13 +8 18 8 18 +8 18 8 18 +8 28 8 18 +8 28 8 18 +NULL NULL 4 14 +NULL NULL 5 15 diff --git ql/src/test/results/clientpositive/llap/skewjoin_union_remove_2.q.out ql/src/test/results/clientpositive/llap/skewjoin_union_remove_2.q.out new file mode 100644 index 0000000000..35ca3af9f8 --- /dev/null +++ ql/src/test/results/clientpositive/llap/skewjoin_union_remove_2.q.out @@ -0,0 +1,203 @@ +PREHOOK: query: CREATE TABLE T1_n8(key STRING, val STRING) +SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1_n8 +POSTHOOK: query: CREATE TABLE T1_n8(key STRING, val STRING) +SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1_n8 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n8 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1_n8 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n8 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1_n8 +PREHOOK: query: CREATE TABLE T2_n4(key STRING, val STRING) +SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T2_n4 +POSTHOOK: query: CREATE TABLE T2_n4(key STRING, val STRING) +SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T2_n4 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n4 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t2_n4 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n4 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t2_n4 +PREHOOK: query: CREATE TABLE T3_n2(key STRING, val STRING) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T3_n2 +POSTHOOK: query: CREATE TABLE T3_n2(key STRING, val STRING) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T3_n2 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n2 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t3_n2 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n2 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t3_n2 +PREHOOK: query: EXPLAIN +SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n8 +PREHOOK: Input: default@t2_n4 +PREHOOK: Input: default@t3_n2 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n8 +POSTHOOK: Input: default@t2_n4 +POSTHOOK: Input: default@t3_n2 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: c + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), val (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key +ORDER BY a.key, b.key, c.key, a.val, b.val, c.val +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n8 +PREHOOK: Input: default@t2_n4 +PREHOOK: Input: default@t3_n2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key +ORDER BY a.key, b.key, c.key, a.val, b.val, c.val +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n8 +POSTHOOK: Input: default@t2_n4 +POSTHOOK: Input: default@t3_n2 +#### A masked pattern was here #### +2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out deleted file mode 100644 index 7f688c57f1..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out +++ /dev/null @@ -1,1654 +0,0 @@ -PREHOOK: query: CREATE TABLE tbl1_n14(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl1_n14 -POSTHOOK: query: CREATE TABLE tbl1_n14(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl1_n14 -PREHOOK: query: CREATE TABLE tbl2_n13(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl2_n13 -POSTHOOK: query: CREATE TABLE tbl2_n13(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl2_n13 -PREHOOK: query: insert overwrite table tbl1_n14 -select * from src where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl1_n14 -POSTHOOK: query: insert overwrite table tbl1_n14 -select * from src where key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@tbl1_n14 -POSTHOOK: Lineage: tbl1_n14.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tbl1_n14.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table tbl2_n13 -select * from src where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl2_n13 -POSTHOOK: query: insert overwrite table tbl2_n13 -select * from src where key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@tbl2_n13 -POSTHOOK: Lineage: tbl2_n13.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tbl2_n13.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain -select count(*) from ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(*) from ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.9375 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) from ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -22 -PREHOOK: query: explain -select key, count(*) from -( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -group by key -order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select key, count(*) from -( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -group by key -order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - minReductionHashAggr: 0.625 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Reducer 3 - Execution mode: vectorized, llap - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, count(*) from -( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -group by key -order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select key, count(*) from -( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key -) subq1 -group by key -order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -0 9 -2 1 -4 1 -5 9 -8 1 -9 1 -PREHOOK: query: explain -select count(*) from -( - select key, count(*) from - ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key - ) subq1 - group by key -) subq2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(*) from -( - select key, count(*) from - ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key - ) subq1 - group by key -) subq2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: int) - minReductionHashAggr: 0.625 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.8333333 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 3 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) from -( - select key, count(*) from - ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key - ) subq1 - group by key -) subq2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from -( - select key, count(*) from - ( - select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from tbl1_n14 a join tbl2_n13 b on a.key = b.key - ) subq1 - group by key -) subq2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -6 -PREHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.8888889 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -20 -PREHOOK: query: explain -select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2_n13 b - on subq2.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2_n13 b - on subq2.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.8888889 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2_n13 b - on subq2.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2_n13 b - on subq2.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -20 -PREHOOK: query: explain -select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.8888889 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(subq2)*/ count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -#### A masked pattern was here #### -20 -PREHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1_n14 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2_n13 a where key < 8) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1_n14 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2_n13 a where key < 8) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 8) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 8) (type: boolean) - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 8) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 8) (type: boolean) - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.9230769 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1_n14 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2_n13 a where key < 8) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1_n14 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2_n13 a where key < 8) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -20 -PREHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1_n14 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2_n13 a) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1_n14 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2_n13 a) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (key + 1) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (key + 1) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.9375 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 3 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1_n14 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2_n13 a) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1_n14 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2_n13 a) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -22 -PREHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.8888889 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(subq1)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -20 -PREHOOK: query: explain -select /*+mapjoin(a)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.8888889 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join tbl2_n13 a on subq1.key = a.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -20 -PREHOOK: query: explain -select /*+mapjoin(subq1, subq2)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on (subq1.key = subq2.key) - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq3 - on (subq1.key = subq3.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(subq1, subq2)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on (subq1.key = subq2.key) - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq3 - on (subq1.key = subq3.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap - Map 5 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.9166667 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 3 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(subq1, subq2)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on subq1.key = subq2.key - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq3 - on (subq1.key = subq3.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(subq1, subq2)*/ count(*) from - (select a.key as key, a.value as value from tbl1_n14 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq2 - on subq1.key = subq2.key - join - (select a.key as key, a.value as value from tbl2_n13 a where key < 6) subq3 - on (subq1.key = subq3.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -56 -PREHOOK: query: explain -select count(*) from ( - select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2_n13 b -on subq2.key = b.key) a -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(*) from ( - select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2_n13 b -on subq2.key = b.key) a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key < 6) (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.8888889 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: llap - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) from ( - select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2_n13 b -on subq2.key = b.key) a -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1_n14 -PREHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from ( - select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1_n14 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2_n13 b -on subq2.key = b.key) a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1_n14 -POSTHOOK: Input: default@tbl2_n13 -#### A masked pattern was here #### -20 diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_15.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_15.q.out deleted file mode 100644 index dbc180ccae..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_15.q.out +++ /dev/null @@ -1,1258 +0,0 @@ -PREHOOK: query: CREATE TABLE test_table1_n4 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, value ASC) INTO 16 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table1_n4 -POSTHOOK: query: CREATE TABLE test_table1_n4 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, value ASC) INTO 16 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table1_n4 -PREHOOK: query: CREATE TABLE test_table2_n4 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, value ASC) INTO 16 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table2_n4 -POSTHOOK: query: CREATE TABLE test_table2_n4 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, value ASC) INTO 16 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table2_n4 -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n4 SELECT * -INSERT OVERWRITE TABLE test_table2_n4 SELECT * -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table1_n4 -PREHOOK: Output: default@test_table2_n4 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n4 SELECT * -INSERT OVERWRITE TABLE test_table2_n4 SELECT * -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table1_n4 -POSTHOOK: Output: default@test_table2_n4 -POSTHOOK: Lineage: test_table1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: test_table2_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table2_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`test_table1_n4` -WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`test_table2_n4` -WHERE `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key` -LIMIT 10 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 5312 - serialization.ddl struct test_table2_n4 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 5312 - serialization.ddl struct test_table2_n4 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n4 - name: default.test_table2_n4 - Truncated Path -> Alias: - /test_table2_n4 [b] - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Position of Big Table: 0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: + - keys: _col0 (type: int) - null sort order: z - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 10 - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Execution mode: llap - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 5312 - serialization.ddl struct test_table1_n4 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 5312 - serialization.ddl struct test_table1_n4 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table1_n4 - name: default.test_table1_n4 - Truncated Path -> Alias: - /test_table1_n4 [a] - Reducer 2 - Execution mode: vectorized, llap - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types int:string:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -2 val_2 2 val_2 -PREHOOK: query: DROP TABLE test_table1_n4 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Output: default@test_table1_n4 -POSTHOOK: query: DROP TABLE test_table1_n4 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Output: default@test_table1_n4 -PREHOOK: query: DROP TABLE test_table2_n4 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@test_table2_n4 -PREHOOK: Output: default@test_table2_n4 -POSTHOOK: query: DROP TABLE test_table2_n4 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@test_table2_n4 -POSTHOOK: Output: default@test_table2_n4 -PREHOOK: query: CREATE TABLE test_table1_n4 (key INT, key2 INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, key2 ASC, value ASC) INTO 16 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table1_n4 -POSTHOOK: query: CREATE TABLE test_table1_n4 (key INT, key2 INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, key2 ASC, value ASC) INTO 16 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table1_n4 -PREHOOK: query: CREATE TABLE test_table2_n4 (key INT, key2 INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, key2 ASC, value ASC) INTO 16 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table2_n4 -POSTHOOK: query: CREATE TABLE test_table2_n4 (key INT, key2 INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC, key2 ASC, value ASC) INTO 16 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table2_n4 -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n4 SELECT key, key, value -INSERT OVERWRITE TABLE test_table2_n4 SELECT key, key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table1_n4 -PREHOOK: Output: default@test_table2_n4 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n4 SELECT key, key, value -INSERT OVERWRITE TABLE test_table2_n4 SELECT key, key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table1_n4 -POSTHOOK: Output: default@test_table2_n4 -POSTHOOK: Lineage: test_table1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table1_n4.key2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: test_table2_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table2_n4.key2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table2_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.key2 = b.key2 ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.key2 = b.key2 ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `key2`, `value` -FROM `default`.`test_table1_n4` -WHERE `key` IS NOT NULL AND `key2` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `key2`, `value` -FROM `default`.`test_table2_n4` -WHERE `key` IS NOT NULL AND `key2` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` AND `t0`.`key2` = `t2`.`key2` -ORDER BY `t0`.`key` -LIMIT 10 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), key2 (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col2 (type: string) - auto parallelism: true - Execution mode: vectorized, llap - LLAP IO: no inputs - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: test_table1_n4 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table1_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table1_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table1_n4 - name: default.test_table1_n4 - Truncated Path -> Alias: - /test_table1_n4 [a] - Map 4 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), key2 (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col2 (type: string) - auto parallelism: true - Execution mode: vectorized, llap - LLAP IO: no inputs - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: test_table2_n4 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n4 - name: default.test_table2_n4 - Truncated Path -> Alias: - /test_table2_n4 [b] - Reducer 2 - Execution mode: llap - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col1 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Position of Big Table: 0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: + - keys: _col0 (type: int) - null sort order: z - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 10 - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) - auto parallelism: false - Reducer 3 - Execution mode: vectorized, llap - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:int:string:int:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.key2 = b.key2 ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.key2 = b.key2 ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -2 2 val_2 2 2 val_2 -PREHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key2 = b.key2 and a.key = b.key ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key2 = b.key2 and a.key = b.key ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `key2`, `value` -FROM `default`.`test_table1_n4` -WHERE `key2` IS NOT NULL AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `key2`, `value` -FROM `default`.`test_table2_n4` -WHERE `key2` IS NOT NULL AND `key` IS NOT NULL) AS `t2` ON `t0`.`key2` = `t2`.`key2` AND `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key` -LIMIT 10 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key2 is not null and key is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key2 is not null and key is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), key2 (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col2 (type: string) - auto parallelism: true - Execution mode: vectorized, llap - LLAP IO: no inputs - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: test_table1_n4 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table1_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table1_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table1_n4 - name: default.test_table1_n4 - Truncated Path -> Alias: - /test_table1_n4 [a] - Map 4 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key2 is not null and key is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key2 is not null and key is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), key2 (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col2 (type: string) - auto parallelism: true - Execution mode: vectorized, llap - LLAP IO: no inputs - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: test_table2_n4 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n4 - name: default.test_table2_n4 - Truncated Path -> Alias: - /test_table2_n4 [b] - Reducer 2 - Execution mode: llap - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col1 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Position of Big Table: 0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: + - keys: _col0 (type: int) - null sort order: z - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 10 - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) - auto parallelism: false - Reducer 3 - Execution mode: vectorized, llap - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:int:string:int:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key2 = b.key2 and a.key = b.key ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key2 = b.key2 and a.key = b.key ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -2 2 val_2 2 2 val_2 -PREHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.value = b.value ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.value = b.value ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `key2`, `value` -FROM `default`.`test_table1_n4` -WHERE `key` IS NOT NULL AND `value` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `key2`, `value` -FROM `default`.`test_table2_n4` -WHERE `key` IS NOT NULL AND `value` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` AND `t0`.`value` = `t2`.`value` -ORDER BY `t0`.`key` -LIMIT 10 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), key2 (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col2 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: int) - auto parallelism: true - Execution mode: vectorized, llap - LLAP IO: no inputs - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: test_table1_n4 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table1_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table1_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table1_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table1_n4 - name: default.test_table1_n4 - Truncated Path -> Alias: - /test_table1_n4 [a] - Map 4 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), key2 (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col2 (type: string) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: int) - auto parallelism: true - Execution mode: vectorized, llap - LLAP IO: no inputs - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: test_table2_n4 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","key2":"true","value":"true"}} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,key2,value - columns.comments - columns.types int:int:string -#### A masked pattern was here #### - name default.test_table2_n4 - numFiles 16 - numRows 500 - rawDataSize 7218 - serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7718 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n4 - name: default.test_table2_n4 - Truncated Path -> Alias: - /test_table2_n4 [b] - Reducer 2 - Execution mode: llap - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col2 (type: string) - 1 _col0 (type: int), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Position of Big Table: 0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Top N Key Operator - sort order: + - keys: _col0 (type: int) - null sort order: z - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - top n: 10 - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 10 - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) - auto parallelism: false - Reducer 3 - Execution mode: vectorized, llap - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:int:string:int:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.value = b.value ORDER BY a.key LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -POSTHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1_n4 a JOIN test_table2_n4 b ON a.key = b.key and a.value = b.value ORDER BY a.key LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Input: default@test_table2_n4 -#### A masked pattern was here #### -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -0 0 val_0 0 0 val_0 -2 2 val_2 2 2 val_2 -PREHOOK: query: DROP TABLE test_table1_n4 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@test_table1_n4 -PREHOOK: Output: default@test_table1_n4 -POSTHOOK: query: DROP TABLE test_table1_n4 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@test_table1_n4 -POSTHOOK: Output: default@test_table1_n4 -PREHOOK: query: DROP TABLE test_table2_n4 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@test_table2_n4 -PREHOOK: Output: default@test_table2_n4 -POSTHOOK: query: DROP TABLE test_table2_n4 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@test_table2_n4 -POSTHOOK: Output: default@test_table2_n4 diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_17.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_17.q.out deleted file mode 100644 index ed70c2ab6a..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_17.q.out +++ /dev/null @@ -1,1867 +0,0 @@ -PREHOOK: query: CREATE TABLE test_table1_n15 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table1_n15 -POSTHOOK: query: CREATE TABLE test_table1_n15 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table1_n15 -PREHOOK: query: CREATE TABLE test_table2_n14 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table2_n14 -POSTHOOK: query: CREATE TABLE test_table2_n14 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table2_n14 -PREHOOK: query: CREATE TABLE test_table3_n7 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table3_n7 -POSTHOOK: query: CREATE TABLE test_table3_n7 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table3_n7 -PREHOOK: query: CREATE TABLE test_table4_n1 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table4_n1 -POSTHOOK: query: CREATE TABLE test_table4_n1 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table4_n1 -PREHOOK: query: CREATE TABLE test_table5 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table5 -POSTHOOK: query: CREATE TABLE test_table5 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table5 -PREHOOK: query: CREATE TABLE test_table6 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table6 -POSTHOOK: query: CREATE TABLE test_table6 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table6 -PREHOOK: query: CREATE TABLE test_table7 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table7 -POSTHOOK: query: CREATE TABLE test_table7 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table7 -PREHOOK: query: CREATE TABLE test_table8 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table8 -POSTHOOK: query: CREATE TABLE test_table8 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table8 -PREHOOK: query: INSERT OVERWRITE TABLE test_table1_n15 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table1_n15 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table1_n15 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table1_n15 -POSTHOOK: Lineage: test_table1_n15.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table1_n15.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: INSERT OVERWRITE TABLE test_table2_n14 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table2_n14 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table2_n14 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table2_n14 -POSTHOOK: Lineage: test_table2_n14.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table2_n14.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: INSERT OVERWRITE TABLE test_table3_n7 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table3_n7 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table3_n7 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table3_n7 -POSTHOOK: Lineage: test_table3_n7.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table3_n7.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: INSERT OVERWRITE TABLE test_table4_n1 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table4_n1 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table4_n1 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table4_n1 -POSTHOOK: Lineage: test_table4_n1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table4_n1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: INSERT OVERWRITE TABLE test_table5 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table5 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table5 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table5 -POSTHOOK: Lineage: test_table5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: INSERT OVERWRITE TABLE test_table6 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table6 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table6 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table6 -POSTHOOK: Lineage: test_table6.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table6.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: INSERT OVERWRITE TABLE test_table7 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table7 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table7 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table7 -POSTHOOK: Lineage: test_table7.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table7.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: INSERT OVERWRITE TABLE test_table8 -SELECT * FROM src WHERE key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table8 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table8 -SELECT * FROM src WHERE key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table8 -POSTHOOK: Lineage: test_table8.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table8.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN -SELECT /*+ mapjoin(b, c, d, e, f, g) */ count(*) -FROM test_table1_n15 a JOIN test_table2_n14 b ON a.key = b.key -JOIN test_table3_n7 c ON a.key = c.key -JOIN test_table4_n1 d ON a.key = d.key -JOIN test_table5 e ON a.key = e.key -JOIN test_table6 f ON a.key = f.key -JOIN test_table7 g ON a.key = g.key -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n15 -PREHOOK: Input: default@test_table2_n14 -PREHOOK: Input: default@test_table3_n7 -PREHOOK: Input: default@test_table4_n1 -PREHOOK: Input: default@test_table5 -PREHOOK: Input: default@test_table6 -PREHOOK: Input: default@test_table7 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT /*+ mapjoin(b, c, d, e, f, g) */ count(*) -FROM test_table1_n15 a JOIN test_table2_n14 b ON a.key = b.key -JOIN test_table3_n7 c ON a.key = c.key -JOIN test_table4_n1 d ON a.key = d.key -JOIN test_table5 e ON a.key = e.key -JOIN test_table6 f ON a.key = f.key -JOIN test_table7 g ON a.key = g.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n15 -POSTHOOK: Input: default@test_table2_n14 -POSTHOOK: Input: default@test_table3_n7 -POSTHOOK: Input: default@test_table4_n1 -POSTHOOK: Input: default@test_table5 -POSTHOOK: Input: default@test_table6 -POSTHOOK: Input: default@test_table7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) - Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) - Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) - Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 6 <- Map 13 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) - Reducer 7 <- Map 14 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) - Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 10 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 11 - Map Operator Tree: - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 12 - Map Operator Tree: - TableScan - alias: e - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 13 - Map Operator Tree: - TableScan - alias: f - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 14 - Map Operator Tree: - TableScan - alias: g - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 9 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 16 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 16 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 4 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 43 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 43 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 71 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 71 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 6 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 118 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 118 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 7 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reducer 8 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT /*+ mapjoin(b, c, d, e, f, g) */ count(*) -FROM test_table1_n15 a JOIN test_table2_n14 b ON a.key = b.key -JOIN test_table3_n7 c ON a.key = c.key -JOIN test_table4_n1 d ON a.key = d.key -JOIN test_table5 e ON a.key = e.key -JOIN test_table6 f ON a.key = f.key -JOIN test_table7 g ON a.key = g.key -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n15 -PREHOOK: Input: default@test_table2_n14 -PREHOOK: Input: default@test_table3_n7 -PREHOOK: Input: default@test_table4_n1 -PREHOOK: Input: default@test_table5 -PREHOOK: Input: default@test_table6 -PREHOOK: Input: default@test_table7 -#### A masked pattern was here #### -POSTHOOK: query: SELECT /*+ mapjoin(b, c, d, e, f, g) */ count(*) -FROM test_table1_n15 a JOIN test_table2_n14 b ON a.key = b.key -JOIN test_table3_n7 c ON a.key = c.key -JOIN test_table4_n1 d ON a.key = d.key -JOIN test_table5 e ON a.key = e.key -JOIN test_table6 f ON a.key = f.key -JOIN test_table7 g ON a.key = g.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n15 -POSTHOOK: Input: default@test_table2_n14 -POSTHOOK: Input: default@test_table3_n7 -POSTHOOK: Input: default@test_table4_n1 -POSTHOOK: Input: default@test_table5 -POSTHOOK: Input: default@test_table6 -POSTHOOK: Input: default@test_table7 -#### A masked pattern was here #### -4378 -PREHOOK: query: EXPLAIN -SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n15 -PREHOOK: Input: default@test_table2_n14 -PREHOOK: Input: default@test_table3_n7 -PREHOOK: Input: default@test_table4_n1 -PREHOOK: Input: default@test_table5 -PREHOOK: Input: default@test_table6 -PREHOOK: Input: default@test_table7 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n15 -POSTHOOK: Input: default@test_table2_n14 -POSTHOOK: Input: default@test_table3_n7 -POSTHOOK: Input: default@test_table4_n1 -POSTHOOK: Input: default@test_table5 -POSTHOOK: Input: default@test_table6 -POSTHOOK: Input: default@test_table7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Map 1 <- Map 3 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE), Map 5 (CUSTOM_EDGE), Map 6 (CUSTOM_EDGE), Map 7 (CUSTOM_EDGE), Map 8 (CUSTOM_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 3 - Statistics: Num rows: 16 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 4 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 5 - Statistics: Num rows: 43 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 6 - Statistics: Num rows: 71 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 7 - Statistics: Num rows: 118 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 8 - Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 3 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: e - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: f - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: g - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n15 -PREHOOK: Input: default@test_table2_n14 -PREHOOK: Input: default@test_table3_n7 -PREHOOK: Input: default@test_table4_n1 -PREHOOK: Input: default@test_table5 -PREHOOK: Input: default@test_table6 -PREHOOK: Input: default@test_table7 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n15 -POSTHOOK: Input: default@test_table2_n14 -POSTHOOK: Input: default@test_table3_n7 -POSTHOOK: Input: default@test_table4_n1 -POSTHOOK: Input: default@test_table5 -POSTHOOK: Input: default@test_table6 -POSTHOOK: Input: default@test_table7 -#### A masked pattern was here #### -4378 -PREHOOK: query: EXPLAIN -SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -LEFT OUTER JOIN test_table8 h ON a.key = h.key -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n15 -PREHOOK: Input: default@test_table2_n14 -PREHOOK: Input: default@test_table3_n7 -PREHOOK: Input: default@test_table4_n1 -PREHOOK: Input: default@test_table5 -PREHOOK: Input: default@test_table6 -PREHOOK: Input: default@test_table7 -PREHOOK: Input: default@test_table8 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -LEFT OUTER JOIN test_table8 h ON a.key = h.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n15 -POSTHOOK: Input: default@test_table2_n14 -POSTHOOK: Input: default@test_table3_n7 -POSTHOOK: Input: default@test_table4_n1 -POSTHOOK: Input: default@test_table5 -POSTHOOK: Input: default@test_table6 -POSTHOOK: Input: default@test_table7 -POSTHOOK: Input: default@test_table8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Map 1 <- Map 3 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE), Map 5 (CUSTOM_EDGE), Map 6 (CUSTOM_EDGE), Map 7 (CUSTOM_EDGE), Map 8 (CUSTOM_EDGE), Map 9 (CUSTOM_EDGE) - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 3 - Statistics: Num rows: 16 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 4 - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 5 - Statistics: Num rows: 43 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 6 - Statistics: Num rows: 71 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 7 - Statistics: Num rows: 118 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - input vertices: - 1 Map 8 - Statistics: Num rows: 196 Data size: 784 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 9 - Statistics: Num rows: 326 Data size: 2608 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 3 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: e - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: f - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: g - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 9 - Map Operator Tree: - TableScan - alias: h - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -LEFT OUTER JOIN test_table8 h ON a.key = h.key -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n15 -PREHOOK: Input: default@test_table2_n14 -PREHOOK: Input: default@test_table3_n7 -PREHOOK: Input: default@test_table4_n1 -PREHOOK: Input: default@test_table5 -PREHOOK: Input: default@test_table6 -PREHOOK: Input: default@test_table7 -PREHOOK: Input: default@test_table8 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(*) -FROM test_table1_n15 a LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -LEFT OUTER JOIN test_table8 h ON a.key = h.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n15 -POSTHOOK: Input: default@test_table2_n14 -POSTHOOK: Input: default@test_table3_n7 -POSTHOOK: Input: default@test_table4_n1 -POSTHOOK: Input: default@test_table5 -POSTHOOK: Input: default@test_table6 -POSTHOOK: Input: default@test_table7 -POSTHOOK: Input: default@test_table8 -#### A masked pattern was here #### -13126 -PREHOOK: query: EXPLAIN -SELECT a.* -FROM test_table1_n15 a -LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -LEFT OUTER JOIN test_table8 h ON a.key = h.key -LEFT OUTER JOIN test_table4_n1 i ON a.key = i.key -LEFT OUTER JOIN test_table5 j ON a.key = j.key -LEFT OUTER JOIN test_table6 k ON a.key = k.key -LEFT OUTER JOIN test_table7 l ON a.key = l.key -LEFT OUTER JOIN test_table8 m ON a.key = m.key -LEFT OUTER JOIN test_table7 n ON a.key = n.key -LEFT OUTER JOIN test_table8 o ON a.key = o.key -LEFT OUTER JOIN test_table4_n1 p ON a.key = p.key -LEFT OUTER JOIN test_table5 q ON a.key = q.key -LEFT OUTER JOIN test_table6 r ON a.key = r.key -LEFT OUTER JOIN test_table7 s ON a.key = s.key -LEFT OUTER JOIN test_table8 t ON a.key = t.key -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n15 -PREHOOK: Input: default@test_table2_n14 -PREHOOK: Input: default@test_table3_n7 -PREHOOK: Input: default@test_table4_n1 -PREHOOK: Input: default@test_table5 -PREHOOK: Input: default@test_table6 -PREHOOK: Input: default@test_table7 -PREHOOK: Input: default@test_table8 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.* -FROM test_table1_n15 a -LEFT OUTER JOIN test_table2_n14 b ON a.key = b.key -LEFT OUTER JOIN test_table3_n7 c ON a.key = c.key -LEFT OUTER JOIN test_table4_n1 d ON a.key = d.key -LEFT OUTER JOIN test_table5 e ON a.key = e.key -LEFT OUTER JOIN test_table6 f ON a.key = f.key -LEFT OUTER JOIN test_table7 g ON a.key = g.key -LEFT OUTER JOIN test_table8 h ON a.key = h.key -LEFT OUTER JOIN test_table4_n1 i ON a.key = i.key -LEFT OUTER JOIN test_table5 j ON a.key = j.key -LEFT OUTER JOIN test_table6 k ON a.key = k.key -LEFT OUTER JOIN test_table7 l ON a.key = l.key -LEFT OUTER JOIN test_table8 m ON a.key = m.key -LEFT OUTER JOIN test_table7 n ON a.key = n.key -LEFT OUTER JOIN test_table8 o ON a.key = o.key -LEFT OUTER JOIN test_table4_n1 p ON a.key = p.key -LEFT OUTER JOIN test_table5 q ON a.key = q.key -LEFT OUTER JOIN test_table6 r ON a.key = r.key -LEFT OUTER JOIN test_table7 s ON a.key = s.key -LEFT OUTER JOIN test_table8 t ON a.key = t.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n15 -POSTHOOK: Input: default@test_table2_n14 -POSTHOOK: Input: default@test_table3_n7 -POSTHOOK: Input: default@test_table4_n1 -POSTHOOK: Input: default@test_table5 -POSTHOOK: Input: default@test_table6 -POSTHOOK: Input: default@test_table7 -POSTHOOK: Input: default@test_table8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Map 1 <- Map 10 (CUSTOM_EDGE), Map 11 (CUSTOM_EDGE), Map 12 (CUSTOM_EDGE), Map 13 (CUSTOM_EDGE), Map 14 (CUSTOM_EDGE), Map 15 (CUSTOM_EDGE), Map 16 (CUSTOM_EDGE), Map 17 (CUSTOM_EDGE), Map 18 (CUSTOM_EDGE), Map 19 (CUSTOM_EDGE), Map 2 (CUSTOM_EDGE), Map 20 (CUSTOM_EDGE), Map 3 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE), Map 5 (CUSTOM_EDGE), Map 6 (CUSTOM_EDGE), Map 7 (CUSTOM_EDGE), Map 8 (CUSTOM_EDGE), Map 9 (CUSTOM_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 2 - Statistics: Num rows: 16 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 3 - Statistics: Num rows: 26 Data size: 2418 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 4 - Statistics: Num rows: 43 Data size: 3999 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 5 - Statistics: Num rows: 71 Data size: 6603 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 6 - Statistics: Num rows: 118 Data size: 10974 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 7 - Statistics: Num rows: 196 Data size: 18228 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 8 - Statistics: Num rows: 326 Data size: 30318 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 9 - Statistics: Num rows: 543 Data size: 50499 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 10 - Statistics: Num rows: 905 Data size: 84165 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 11 - Statistics: Num rows: 1508 Data size: 140244 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 12 - Statistics: Num rows: 2513 Data size: 233709 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 13 - Statistics: Num rows: 4188 Data size: 389484 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 14 - Statistics: Num rows: 6980 Data size: 649140 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 15 - Statistics: Num rows: 11633 Data size: 1081869 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 16 - Statistics: Num rows: 19388 Data size: 1803084 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 17 - Statistics: Num rows: 32313 Data size: 3005109 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 18 - Statistics: Num rows: 53855 Data size: 5008515 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 19 - Statistics: Num rows: 89758 Data size: 8347494 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 20 - Statistics: Num rows: 149596 Data size: 13912428 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 149596 Data size: 13912428 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 10 - Map Operator Tree: - TableScan - alias: j - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 11 - Map Operator Tree: - TableScan - alias: k - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 12 - Map Operator Tree: - TableScan - alias: l - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 13 - Map Operator Tree: - TableScan - alias: m - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 14 - Map Operator Tree: - TableScan - alias: n - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 15 - Map Operator Tree: - TableScan - alias: o - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 16 - Map Operator Tree: - TableScan - alias: p - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 17 - Map Operator Tree: - TableScan - alias: q - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 18 - Map Operator Tree: - TableScan - alias: r - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 19 - Map Operator Tree: - TableScan - alias: s - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 2 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 20 - Map Operator Tree: - TableScan - alias: t - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 3 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: e - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 6 - Map Operator Tree: - TableScan - alias: f - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 7 - Map Operator Tree: - TableScan - alias: g - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 8 - Map Operator Tree: - TableScan - alias: h - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 9 - Map Operator Tree: - TableScan - alias: i - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized, llap - LLAP IO: no inputs - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_18.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_18.q.out deleted file mode 100644 index 80a9888ca8..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_18.q.out +++ /dev/null @@ -1,544 +0,0 @@ -PREHOOK: query: CREATE TABLE test_table1_n7 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table1_n7 -POSTHOOK: query: CREATE TABLE test_table1_n7 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table1_n7 -PREHOOK: query: CREATE TABLE test_table2_n7 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table2_n7 -POSTHOOK: query: CREATE TABLE test_table2_n7 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table2_n7 -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n7 PARTITION (ds = '1') SELECT * -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table1_n7@ds=1 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n7 PARTITION (ds = '1') SELECT * -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table1_n7@ds=1 -POSTHOOK: Lineage: test_table1_n7 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table1_n7 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -PREHOOK: Output: default@test_table2_n7@ds=1 -POSTHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -POSTHOOK: Output: default@test_table2_n7@ds=1 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n7 - Execution mode: vectorized, llap - LLAP IO: no inputs - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds 1 - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n7 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.test_table2_n7 - -PREHOOK: query: INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -PREHOOK: Output: default@test_table2_n7@ds=1 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -POSTHOOK: Output: default@test_table2_n7@ds=1 -POSTHOOK: Lineage: test_table2_n7 PARTITION(ds=1).key SIMPLE [(test_table1_n7)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: test_table2_n7 PARTITION(ds=1).value SIMPLE [(test_table1_n7)a.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select count(*) from test_table1_n7 where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n7 where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -#### A masked pattern was here #### -500 -PREHOOK: query: select count(*) from test_table1_n7 where ds = '1' and hash(key) % 2 = 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n7 where ds = '1' and hash(key) % 2 = 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -247 -PREHOOK: query: select count(*) from test_table1_n7 where ds = '1' and hash(key) % 2 = 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n7 where ds = '1' and hash(key) % 2 = 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -253 -PREHOOK: query: select count(*) from test_table1_n7 tablesample (bucket 1 out of 2) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n7 tablesample (bucket 1 out of 2) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -243 -PREHOOK: query: select count(*) from test_table1_n7 tablesample (bucket 2 out of 2) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n7 tablesample (bucket 2 out of 2) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -#### A masked pattern was here #### -257 -PREHOOK: query: select count(*) from test_table2_n7 where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -500 -PREHOOK: query: select count(*) from test_table2_n7 where ds = '1' and hash(key) % 2 = 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '1' and hash(key) % 2 = 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -247 -PREHOOK: query: select count(*) from test_table2_n7 where ds = '1' and hash(key) % 2 = 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '1' and hash(key) % 2 = 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -253 -PREHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 1 out of 2) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 1 out of 2) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -243 -PREHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 2 out of 2) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 2 out of 2) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=1 -#### A masked pattern was here #### -257 -PREHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '2') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' and a.key = 238 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -PREHOOK: Output: default@test_table2_n7@ds=2 -POSTHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '2') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' and a.key = 238 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -POSTHOOK: Output: default@test_table2_n7@ds=2 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key = 238) and (ds = '1')) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 238) (type: boolean) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 238 (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n7 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2' (type: string) - outputColumnNames: key, value, ds - Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - keys: ds (type: string) - minReductionHashAggr: 0.5 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: struct), _col2 (type: struct) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds 2 - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n7 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.test_table2_n7 - -PREHOOK: query: INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '2') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' and a.key = 238 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n7 -PREHOOK: Input: default@test_table1_n7@ds=1 -PREHOOK: Output: default@test_table2_n7@ds=2 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '2') -SELECT a.key, a.value FROM test_table1_n7 a WHERE a.ds = '1' and a.key = 238 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n7 -POSTHOOK: Input: default@test_table1_n7@ds=1 -POSTHOOK: Output: default@test_table2_n7@ds=2 -POSTHOOK: Lineage: test_table2_n7 PARTITION(ds=2).key SIMPLE [] -POSTHOOK: Lineage: test_table2_n7 PARTITION(ds=2).value SIMPLE [(test_table1_n7)a.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select count(*) from test_table2_n7 where ds = '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -2 -PREHOOK: query: select count(*) from test_table2_n7 where ds = '2' and hash(key) % 2 = 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '2' and hash(key) % 2 = 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -2 -PREHOOK: query: select count(*) from test_table2_n7 where ds = '2' and hash(key) % 2 = 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '2' and hash(key) % 2 = 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -0 -PREHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 1 out of 2) s where ds = '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 1 out of 2) s where ds = '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -2 -PREHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 2 out of 2) s where ds = '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 2 out of 2) s where ds = '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=2 -#### A masked pattern was here #### -0 -PREHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '3') -SELECT a.key, a.value FROM test_table2_n7 a WHERE a.ds = '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=2 -PREHOOK: Output: default@test_table2_n7@ds=3 -POSTHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '3') -SELECT a.key, a.value FROM test_table2_n7 a WHERE a.ds = '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=2 -POSTHOOK: Output: default@test_table2_n7@ds=3 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (ds = '2') (type: boolean) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n7 - Execution mode: vectorized, llap - LLAP IO: no inputs - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds 3 - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n7 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.test_table2_n7 - -PREHOOK: query: INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '2') -SELECT a.key, a.value FROM test_table2_n7 a WHERE a.ds = '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -PREHOOK: Input: default@test_table2_n7@ds=2 -PREHOOK: Output: default@test_table2_n7@ds=2 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table2_n7 PARTITION (ds = '2') -SELECT a.key, a.value FROM test_table2_n7 a WHERE a.ds = '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -POSTHOOK: Input: default@test_table2_n7@ds=2 -POSTHOOK: Output: default@test_table2_n7@ds=2 -POSTHOOK: Lineage: test_table2_n7 PARTITION(ds=2).key SIMPLE [(test_table2_n7)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: test_table2_n7 PARTITION(ds=2).value SIMPLE [(test_table2_n7)a.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select count(*) from test_table2_n7 where ds = '3' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '3' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -0 -PREHOOK: query: select count(*) from test_table2_n7 where ds = '3' and hash(key) % 2 = 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '3' and hash(key) % 2 = 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -0 -PREHOOK: query: select count(*) from test_table2_n7 where ds = '3' and hash(key) % 2 = 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 where ds = '3' and hash(key) % 2 = 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -0 -PREHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 1 out of 2) s where ds = '3' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 1 out of 2) s where ds = '3' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -0 -PREHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 2 out of 2) s where ds = '3' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n7 tablesample (bucket 2 out of 2) s where ds = '3' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n7 -#### A masked pattern was here #### -0 diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_19.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_19.q.out deleted file mode 100644 index 81c6417354..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_19.q.out +++ /dev/null @@ -1,265 +0,0 @@ -PREHOOK: query: CREATE TABLE test_table1_n11 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table1_n11 -POSTHOOK: query: CREATE TABLE test_table1_n11 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table1_n11 -PREHOOK: query: CREATE TABLE test_table2_n11 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_table2_n11 -POSTHOOK: query: CREATE TABLE test_table2_n11 (key INT, value STRING) PARTITIONED BY (ds STRING) -CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_table2_n11 -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n11 PARTITION (ds = '1') SELECT * -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@test_table1_n11@ds=1 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE test_table1_n11 PARTITION (ds = '1') SELECT * -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@test_table1_n11@ds=1 -POSTHOOK: Lineage: test_table1_n11 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: test_table1_n11 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n11 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n11 a WHERE a.ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -PREHOOK: Output: default@test_table2_n11@ds=1 -POSTHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE test_table2_n11 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n11 a WHERE a.ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -POSTHOOK: Output: default@test_table2_n11@ds=1 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - filterExpr: (ds = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n11 - Execution mode: vectorized, llap - LLAP IO: no inputs - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds 1 - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2_n11 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.test_table2_n11 - -PREHOOK: query: INSERT OVERWRITE TABLE test_table2_n11 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n11 a WHERE a.ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -PREHOOK: Output: default@test_table2_n11@ds=1 -POSTHOOK: query: INSERT OVERWRITE TABLE test_table2_n11 PARTITION (ds = '1') -SELECT a.key, a.value FROM test_table1_n11 a WHERE a.ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -POSTHOOK: Output: default@test_table2_n11@ds=1 -POSTHOOK: Lineage: test_table2_n11 PARTITION(ds=1).key SIMPLE [(test_table1_n11)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: test_table2_n11 PARTITION(ds=1).value SIMPLE [(test_table1_n11)a.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select count(*) from test_table1_n11 where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n11 where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -#### A masked pattern was here #### -500 -PREHOOK: query: select count(*) from test_table1_n11 where ds = '1' and hash(key) % 16 = 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n11 where ds = '1' and hash(key) % 16 = 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -36 -PREHOOK: query: select count(*) from test_table1_n11 where ds = '1' and hash(key) % 16 = 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n11 where ds = '1' and hash(key) % 16 = 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -40 -PREHOOK: query: select count(*) from test_table1_n11 where ds = '1' and hash(key) % 16 = 12 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n11 where ds = '1' and hash(key) % 16 = 12 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -29 -PREHOOK: query: select count(*) from test_table1_n11 tablesample (bucket 1 out of 16) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n11 tablesample (bucket 1 out of 16) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -36 -PREHOOK: query: select count(*) from test_table1_n11 tablesample (bucket 6 out of 16) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n11 tablesample (bucket 6 out of 16) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -19 -PREHOOK: query: select count(*) from test_table1_n11 tablesample (bucket 13 out of 16) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table1_n11 -PREHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table1_n11 tablesample (bucket 13 out of 16) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table1_n11 -POSTHOOK: Input: default@test_table1_n11@ds=1 -#### A masked pattern was here #### -33 -PREHOOK: query: select count(*) from test_table2_n11 where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n11 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n11 where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n11 -#### A masked pattern was here #### -500 -PREHOOK: query: select count(*) from test_table2_n11 where ds = '1' and hash(key) % 16 = 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n11 -PREHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n11 where ds = '1' and hash(key) % 16 = 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n11 -POSTHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -36 -PREHOOK: query: select count(*) from test_table2_n11 where ds = '1' and hash(key) % 16 = 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n11 -PREHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n11 where ds = '1' and hash(key) % 16 = 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n11 -POSTHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -40 -PREHOOK: query: select count(*) from test_table2_n11 where ds = '1' and hash(key) % 16 = 12 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n11 -PREHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n11 where ds = '1' and hash(key) % 16 = 12 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n11 -POSTHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -29 -PREHOOK: query: select count(*) from test_table2_n11 tablesample (bucket 1 out of 16) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n11 -PREHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n11 tablesample (bucket 1 out of 16) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n11 -POSTHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -36 -PREHOOK: query: select count(*) from test_table2_n11 tablesample (bucket 6 out of 16) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n11 -PREHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n11 tablesample (bucket 6 out of 16) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n11 -POSTHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -19 -PREHOOK: query: select count(*) from test_table2_n11 tablesample (bucket 13 out of 16) s where ds = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_table2_n11 -PREHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from test_table2_n11 tablesample (bucket 13 out of 16) s where ds = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_table2_n11 -POSTHOOK: Input: default@test_table2_n11@ds=1 -#### A masked pattern was here #### -33 diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_4.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_4.q.out deleted file mode 100644 index 2243c75d92..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_4.q.out +++ /dev/null @@ -1,1757 +0,0 @@ -PREHOOK: query: create table smb_bucket_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket_1 -POSTHOOK: query: create table smb_bucket_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket_1 -PREHOOK: query: create table smb_bucket_2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket_2 -POSTHOOK: query: create table smb_bucket_2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket_2 -PREHOOK: query: create table smb_bucket_3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket_3 -POSTHOOK: query: create table smb_bucket_3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket_3 -PREHOOK: query: load data local inpath '../../data/files/smb_rc1/000000_0' overwrite into table smb_bucket_1 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@smb_bucket_1 -POSTHOOK: query: load data local inpath '../../data/files/smb_rc1/000000_0' overwrite into table smb_bucket_1 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@smb_bucket_1 -PREHOOK: query: load data local inpath '../../data/files/smb_rc2/000000_0' overwrite into table smb_bucket_2 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@smb_bucket_2 -POSTHOOK: query: load data local inpath '../../data/files/smb_rc2/000000_0' overwrite into table smb_bucket_2 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@smb_bucket_2 -PREHOOK: query: load data local inpath '../../data/files/smb_rc3/000000_0' overwrite into table smb_bucket_3 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@smb_bucket_3 -POSTHOOK: query: load data local inpath '../../data/files/smb_rc3/000000_0' overwrite into table smb_bucket_3 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@smb_bucket_3 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 20 val_20 -NULL NULL NULL NULL 23 val_23 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 20 val_20 -NULL NULL NULL NULL 23 val_23 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1 -PREHOOK: Input: default@smb_bucket_2 -PREHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key full outer join smb_bucket_3 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1 -POSTHOOK: Input: default@smb_bucket_2 -POSTHOOK: Input: default@smb_bucket_3 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_5.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_5.q.out deleted file mode 100644 index f8e1010e2e..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_5.q.out +++ /dev/null @@ -1,1757 +0,0 @@ -PREHOOK: query: create table smb_bucket_1_n2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket_1_n2 -POSTHOOK: query: create table smb_bucket_1_n2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket_1_n2 -PREHOOK: query: create table smb_bucket_2_n2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket_2_n2 -POSTHOOK: query: create table smb_bucket_2_n2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket_2_n2 -PREHOOK: query: create table smb_bucket_3_n2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket_3_n2 -POSTHOOK: query: create table smb_bucket_3_n2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket_3_n2 -PREHOOK: query: load data local inpath '../../data/files/smb_rc1/000000_0' overwrite into table smb_bucket_1_n2 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@smb_bucket_1_n2 -POSTHOOK: query: load data local inpath '../../data/files/smb_rc1/000000_0' overwrite into table smb_bucket_1_n2 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@smb_bucket_1_n2 -PREHOOK: query: load data local inpath '../../data/files/smb_rc2/000000_0' overwrite into table smb_bucket_2_n2 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@smb_bucket_2_n2 -POSTHOOK: query: load data local inpath '../../data/files/smb_rc2/000000_0' overwrite into table smb_bucket_2_n2 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@smb_bucket_2_n2 -PREHOOK: query: load data local inpath '../../data/files/smb_rc3/000000_0' overwrite into table smb_bucket_3_n2 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@smb_bucket_3_n2 -POSTHOOK: query: load data local inpath '../../data/files/smb_rc3/000000_0' overwrite into table smb_bucket_3_n2 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@smb_bucket_3_n2 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 20 val_20 -NULL NULL NULL NULL 23 val_23 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a left outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 20 val_20 -NULL NULL NULL NULL 23 val_23 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a right outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key left outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 2 - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dummy Store - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key right outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 -PREHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 5 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_1_n2 -PREHOOK: Input: default@smb_bucket_2_n2 -PREHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a,c)*/ * from smb_bucket_1_n2 a full outer join smb_bucket_2_n2 b on a.key = b.key full outer join smb_bucket_3_n2 c on b.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_1_n2 -POSTHOOK: Input: default@smb_bucket_2_n2 -POSTHOOK: Input: default@smb_bucket_3_n2 -#### A masked pattern was here #### -1 val_1 NULL NULL NULL NULL -10 val_10 NULL NULL NULL NULL -3 val_3 NULL NULL NULL NULL -4 val_4 NULL NULL NULL NULL -5 val_5 NULL NULL NULL NULL -NULL NULL 20 val_20 20 val_20 -NULL NULL 23 val_23 23 val_23 -NULL NULL 25 val_25 NULL NULL -NULL NULL 30 val_30 NULL NULL -NULL NULL NULL NULL 10 val_10 -NULL NULL NULL NULL 17 val_17 -NULL NULL NULL NULL 19 val_19 -NULL NULL NULL NULL 4 val_4 diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out deleted file mode 100644 index c1efe543af..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out +++ /dev/null @@ -1,2887 +0,0 @@ -PREHOOK: query: CREATE TABLE smb_bucket4_1_n0(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket4_1_n0 -POSTHOOK: query: CREATE TABLE smb_bucket4_1_n0(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket4_1_n0 -PREHOOK: query: CREATE TABLE smb_bucket4_2_n0(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket4_2_n0 -POSTHOOK: query: CREATE TABLE smb_bucket4_2_n0(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket4_2_n0 -PREHOOK: query: create table smb_join_results_n0(k1 int, v1 string, k2 int, v2 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: create table smb_join_results_n0(k1 int, v1 string, k2 int, v2 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_join_results_n0 -PREHOOK: query: create table normal_join_results_n0(k1 int, v1 string, k2 int, v2 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@normal_join_results_n0 -POSTHOOK: query: create table normal_join_results_n0(k1 int, v1 string, k2 int, v2 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@normal_join_results_n0 -PREHOOK: query: insert overwrite table smb_bucket4_1_n0 -select * from src -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@smb_bucket4_1_n0 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n0 -select * from src -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@smb_bucket4_1_n0 -POSTHOOK: Lineage: smb_bucket4_1_n0.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: smb_bucket4_1_n0.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n0 -select * from src -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@smb_bucket4_2_n0 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n0 -select * from src -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@smb_bucket4_2_n0 -POSTHOOK: Lineage: smb_bucket4_2_n0.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: smb_bucket4_2_n0.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, v1, k2, v2 - Column Types: int, string, int, string - Table: default.smb_join_results_n0 - -PREHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -POSTHOOK: Lineage: smb_join_results_n0.k1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.k2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select * from smb_join_results_n0 order by k1 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * from smb_join_results_n0 order by k1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -2 val_2 2 val_2 -4 val_4 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -8 val_8 8 val_8 -9 val_9 9 val_9 -10 val_10 10 val_10 -11 val_11 11 val_11 -12 val_12 12 val_12 -12 val_12 12 val_12 -12 val_12 12 val_12 -12 val_12 12 val_12 -15 val_15 15 val_15 -15 val_15 15 val_15 -15 val_15 15 val_15 -15 val_15 15 val_15 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -20 val_20 20 val_20 -24 val_24 24 val_24 -24 val_24 24 val_24 -24 val_24 24 val_24 -24 val_24 24 val_24 -26 val_26 26 val_26 -26 val_26 26 val_26 -26 val_26 26 val_26 -26 val_26 26 val_26 -27 val_27 27 val_27 -28 val_28 28 val_28 -30 val_30 30 val_30 -33 val_33 33 val_33 -34 val_34 34 val_34 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -37 val_37 37 val_37 -37 val_37 37 val_37 -37 val_37 37 val_37 -37 val_37 37 val_37 -41 val_41 41 val_41 -42 val_42 42 val_42 -42 val_42 42 val_42 -42 val_42 42 val_42 -42 val_42 42 val_42 -43 val_43 43 val_43 -44 val_44 44 val_44 -47 val_47 47 val_47 -51 val_51 51 val_51 -51 val_51 51 val_51 -51 val_51 51 val_51 -51 val_51 51 val_51 -53 val_53 53 val_53 -54 val_54 54 val_54 -57 val_57 57 val_57 -58 val_58 58 val_58 -58 val_58 58 val_58 -58 val_58 58 val_58 -58 val_58 58 val_58 -64 val_64 64 val_64 -65 val_65 65 val_65 -66 val_66 66 val_66 -67 val_67 67 val_67 -67 val_67 67 val_67 -67 val_67 67 val_67 -67 val_67 67 val_67 -69 val_69 69 val_69 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -72 val_72 72 val_72 -72 val_72 72 val_72 -72 val_72 72 val_72 -72 val_72 72 val_72 -74 val_74 74 val_74 -76 val_76 76 val_76 -76 val_76 76 val_76 -76 val_76 76 val_76 -76 val_76 76 val_76 -77 val_77 77 val_77 -78 val_78 78 val_78 -80 val_80 80 val_80 -82 val_82 82 val_82 -83 val_83 83 val_83 -83 val_83 83 val_83 -83 val_83 83 val_83 -83 val_83 83 val_83 -84 val_84 84 val_84 -84 val_84 84 val_84 -84 val_84 84 val_84 -84 val_84 84 val_84 -85 val_85 85 val_85 -86 val_86 86 val_86 -87 val_87 87 val_87 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -92 val_92 92 val_92 -95 val_95 95 val_95 -95 val_95 95 val_95 -95 val_95 95 val_95 -95 val_95 95 val_95 -96 val_96 96 val_96 -97 val_97 97 val_97 -97 val_97 97 val_97 -97 val_97 97 val_97 -97 val_97 97 val_97 -98 val_98 98 val_98 -98 val_98 98 val_98 -98 val_98 98 val_98 -98 val_98 98 val_98 -100 val_100 100 val_100 -100 val_100 100 val_100 -100 val_100 100 val_100 -100 val_100 100 val_100 -103 val_103 103 val_103 -103 val_103 103 val_103 -103 val_103 103 val_103 -103 val_103 103 val_103 -104 val_104 104 val_104 -104 val_104 104 val_104 -104 val_104 104 val_104 -104 val_104 104 val_104 -105 val_105 105 val_105 -111 val_111 111 val_111 -113 val_113 113 val_113 -113 val_113 113 val_113 -113 val_113 113 val_113 -113 val_113 113 val_113 -114 val_114 114 val_114 -116 val_116 116 val_116 -118 val_118 118 val_118 -118 val_118 118 val_118 -118 val_118 118 val_118 -118 val_118 118 val_118 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -120 val_120 120 val_120 -120 val_120 120 val_120 -120 val_120 120 val_120 -120 val_120 120 val_120 -125 val_125 125 val_125 -125 val_125 125 val_125 -125 val_125 125 val_125 -125 val_125 125 val_125 -126 val_126 126 val_126 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -129 val_129 129 val_129 -129 val_129 129 val_129 -129 val_129 129 val_129 -129 val_129 129 val_129 -131 val_131 131 val_131 -133 val_133 133 val_133 -134 val_134 134 val_134 -134 val_134 134 val_134 -134 val_134 134 val_134 -134 val_134 134 val_134 -136 val_136 136 val_136 -137 val_137 137 val_137 -137 val_137 137 val_137 -137 val_137 137 val_137 -137 val_137 137 val_137 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -143 val_143 143 val_143 -145 val_145 145 val_145 -146 val_146 146 val_146 -146 val_146 146 val_146 -146 val_146 146 val_146 -146 val_146 146 val_146 -149 val_149 149 val_149 -149 val_149 149 val_149 -149 val_149 149 val_149 -149 val_149 149 val_149 -150 val_150 150 val_150 -152 val_152 152 val_152 -152 val_152 152 val_152 -152 val_152 152 val_152 -152 val_152 152 val_152 -153 val_153 153 val_153 -155 val_155 155 val_155 -156 val_156 156 val_156 -157 val_157 157 val_157 -158 val_158 158 val_158 -160 val_160 160 val_160 -162 val_162 162 val_162 -163 val_163 163 val_163 -164 val_164 164 val_164 -164 val_164 164 val_164 -164 val_164 164 val_164 -164 val_164 164 val_164 -165 val_165 165 val_165 -165 val_165 165 val_165 -165 val_165 165 val_165 -165 val_165 165 val_165 -166 val_166 166 val_166 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -168 val_168 168 val_168 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -170 val_170 170 val_170 -172 val_172 172 val_172 -172 val_172 172 val_172 -172 val_172 172 val_172 -172 val_172 172 val_172 -174 val_174 174 val_174 -174 val_174 174 val_174 -174 val_174 174 val_174 -174 val_174 174 val_174 -175 val_175 175 val_175 -175 val_175 175 val_175 -175 val_175 175 val_175 -175 val_175 175 val_175 -176 val_176 176 val_176 -176 val_176 176 val_176 -176 val_176 176 val_176 -176 val_176 176 val_176 -177 val_177 177 val_177 -178 val_178 178 val_178 -179 val_179 179 val_179 -179 val_179 179 val_179 -179 val_179 179 val_179 -179 val_179 179 val_179 -180 val_180 180 val_180 -181 val_181 181 val_181 -183 val_183 183 val_183 -186 val_186 186 val_186 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -189 val_189 189 val_189 -190 val_190 190 val_190 -191 val_191 191 val_191 -191 val_191 191 val_191 -191 val_191 191 val_191 -191 val_191 191 val_191 -192 val_192 192 val_192 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -194 val_194 194 val_194 -195 val_195 195 val_195 -195 val_195 195 val_195 -195 val_195 195 val_195 -195 val_195 195 val_195 -196 val_196 196 val_196 -197 val_197 197 val_197 -197 val_197 197 val_197 -197 val_197 197 val_197 -197 val_197 197 val_197 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -200 val_200 200 val_200 -200 val_200 200 val_200 -200 val_200 200 val_200 -200 val_200 200 val_200 -201 val_201 201 val_201 -202 val_202 202 val_202 -203 val_203 203 val_203 -203 val_203 203 val_203 -203 val_203 203 val_203 -203 val_203 203 val_203 -205 val_205 205 val_205 -205 val_205 205 val_205 -205 val_205 205 val_205 -205 val_205 205 val_205 -207 val_207 207 val_207 -207 val_207 207 val_207 -207 val_207 207 val_207 -207 val_207 207 val_207 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -209 val_209 209 val_209 -209 val_209 209 val_209 -209 val_209 209 val_209 -209 val_209 209 val_209 -213 val_213 213 val_213 -213 val_213 213 val_213 -213 val_213 213 val_213 -213 val_213 213 val_213 -214 val_214 214 val_214 -216 val_216 216 val_216 -216 val_216 216 val_216 -216 val_216 216 val_216 -216 val_216 216 val_216 -217 val_217 217 val_217 -217 val_217 217 val_217 -217 val_217 217 val_217 -217 val_217 217 val_217 -218 val_218 218 val_218 -219 val_219 219 val_219 -219 val_219 219 val_219 -219 val_219 219 val_219 -219 val_219 219 val_219 -221 val_221 221 val_221 -221 val_221 221 val_221 -221 val_221 221 val_221 -221 val_221 221 val_221 -222 val_222 222 val_222 -223 val_223 223 val_223 -223 val_223 223 val_223 -223 val_223 223 val_223 -223 val_223 223 val_223 -224 val_224 224 val_224 -224 val_224 224 val_224 -224 val_224 224 val_224 -224 val_224 224 val_224 -226 val_226 226 val_226 -228 val_228 228 val_228 -229 val_229 229 val_229 -229 val_229 229 val_229 -229 val_229 229 val_229 -229 val_229 229 val_229 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -233 val_233 233 val_233 -233 val_233 233 val_233 -233 val_233 233 val_233 -233 val_233 233 val_233 -235 val_235 235 val_235 -237 val_237 237 val_237 -237 val_237 237 val_237 -237 val_237 237 val_237 -237 val_237 237 val_237 -238 val_238 238 val_238 -238 val_238 238 val_238 -238 val_238 238 val_238 -238 val_238 238 val_238 -239 val_239 239 val_239 -239 val_239 239 val_239 -239 val_239 239 val_239 -239 val_239 239 val_239 -241 val_241 241 val_241 -242 val_242 242 val_242 -242 val_242 242 val_242 -242 val_242 242 val_242 -242 val_242 242 val_242 -244 val_244 244 val_244 -247 val_247 247 val_247 -248 val_248 248 val_248 -249 val_249 249 val_249 -252 val_252 252 val_252 -255 val_255 255 val_255 -255 val_255 255 val_255 -255 val_255 255 val_255 -255 val_255 255 val_255 -256 val_256 256 val_256 -256 val_256 256 val_256 -256 val_256 256 val_256 -256 val_256 256 val_256 -257 val_257 257 val_257 -258 val_258 258 val_258 -260 val_260 260 val_260 -262 val_262 262 val_262 -263 val_263 263 val_263 -265 val_265 265 val_265 -265 val_265 265 val_265 -265 val_265 265 val_265 -265 val_265 265 val_265 -266 val_266 266 val_266 -272 val_272 272 val_272 -272 val_272 272 val_272 -272 val_272 272 val_272 -272 val_272 272 val_272 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -274 val_274 274 val_274 -275 val_275 275 val_275 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -278 val_278 278 val_278 -278 val_278 278 val_278 -278 val_278 278 val_278 -278 val_278 278 val_278 -280 val_280 280 val_280 -280 val_280 280 val_280 -280 val_280 280 val_280 -280 val_280 280 val_280 -281 val_281 281 val_281 -281 val_281 281 val_281 -281 val_281 281 val_281 -281 val_281 281 val_281 -282 val_282 282 val_282 -282 val_282 282 val_282 -282 val_282 282 val_282 -282 val_282 282 val_282 -283 val_283 283 val_283 -284 val_284 284 val_284 -285 val_285 285 val_285 -286 val_286 286 val_286 -287 val_287 287 val_287 -288 val_288 288 val_288 -288 val_288 288 val_288 -288 val_288 288 val_288 -288 val_288 288 val_288 -289 val_289 289 val_289 -291 val_291 291 val_291 -292 val_292 292 val_292 -296 val_296 296 val_296 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -302 val_302 302 val_302 -305 val_305 305 val_305 -306 val_306 306 val_306 -307 val_307 307 val_307 -307 val_307 307 val_307 -307 val_307 307 val_307 -307 val_307 307 val_307 -308 val_308 308 val_308 -309 val_309 309 val_309 -309 val_309 309 val_309 -309 val_309 309 val_309 -309 val_309 309 val_309 -310 val_310 310 val_310 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -315 val_315 315 val_315 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -317 val_317 317 val_317 -317 val_317 317 val_317 -317 val_317 317 val_317 -317 val_317 317 val_317 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -321 val_321 321 val_321 -321 val_321 321 val_321 -321 val_321 321 val_321 -321 val_321 321 val_321 -322 val_322 322 val_322 -322 val_322 322 val_322 -322 val_322 322 val_322 -322 val_322 322 val_322 -323 val_323 323 val_323 -325 val_325 325 val_325 -325 val_325 325 val_325 -325 val_325 325 val_325 -325 val_325 325 val_325 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -331 val_331 331 val_331 -331 val_331 331 val_331 -331 val_331 331 val_331 -331 val_331 331 val_331 -332 val_332 332 val_332 -333 val_333 333 val_333 -333 val_333 333 val_333 -333 val_333 333 val_333 -333 val_333 333 val_333 -335 val_335 335 val_335 -336 val_336 336 val_336 -338 val_338 338 val_338 -339 val_339 339 val_339 -341 val_341 341 val_341 -342 val_342 342 val_342 -342 val_342 342 val_342 -342 val_342 342 val_342 -342 val_342 342 val_342 -344 val_344 344 val_344 -344 val_344 344 val_344 -344 val_344 344 val_344 -344 val_344 344 val_344 -345 val_345 345 val_345 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -351 val_351 351 val_351 -353 val_353 353 val_353 -353 val_353 353 val_353 -353 val_353 353 val_353 -353 val_353 353 val_353 -356 val_356 356 val_356 -360 val_360 360 val_360 -362 val_362 362 val_362 -364 val_364 364 val_364 -365 val_365 365 val_365 -366 val_366 366 val_366 -367 val_367 367 val_367 -367 val_367 367 val_367 -367 val_367 367 val_367 -367 val_367 367 val_367 -368 val_368 368 val_368 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -373 val_373 373 val_373 -374 val_374 374 val_374 -375 val_375 375 val_375 -377 val_377 377 val_377 -378 val_378 378 val_378 -379 val_379 379 val_379 -382 val_382 382 val_382 -382 val_382 382 val_382 -382 val_382 382 val_382 -382 val_382 382 val_382 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -386 val_386 386 val_386 -389 val_389 389 val_389 -392 val_392 392 val_392 -393 val_393 393 val_393 -394 val_394 394 val_394 -395 val_395 395 val_395 -395 val_395 395 val_395 -395 val_395 395 val_395 -395 val_395 395 val_395 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -397 val_397 397 val_397 -397 val_397 397 val_397 -397 val_397 397 val_397 -397 val_397 397 val_397 -399 val_399 399 val_399 -399 val_399 399 val_399 -399 val_399 399 val_399 -399 val_399 399 val_399 -400 val_400 400 val_400 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -402 val_402 402 val_402 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -404 val_404 404 val_404 -404 val_404 404 val_404 -404 val_404 404 val_404 -404 val_404 404 val_404 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -407 val_407 407 val_407 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -411 val_411 411 val_411 -413 val_413 413 val_413 -413 val_413 413 val_413 -413 val_413 413 val_413 -413 val_413 413 val_413 -414 val_414 414 val_414 -414 val_414 414 val_414 -414 val_414 414 val_414 -414 val_414 414 val_414 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -418 val_418 418 val_418 -419 val_419 419 val_419 -421 val_421 421 val_421 -424 val_424 424 val_424 -424 val_424 424 val_424 -424 val_424 424 val_424 -424 val_424 424 val_424 -427 val_427 427 val_427 -429 val_429 429 val_429 -429 val_429 429 val_429 -429 val_429 429 val_429 -429 val_429 429 val_429 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -432 val_432 432 val_432 -435 val_435 435 val_435 -436 val_436 436 val_436 -437 val_437 437 val_437 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -439 val_439 439 val_439 -439 val_439 439 val_439 -439 val_439 439 val_439 -439 val_439 439 val_439 -443 val_443 443 val_443 -444 val_444 444 val_444 -446 val_446 446 val_446 -448 val_448 448 val_448 -449 val_449 449 val_449 -452 val_452 452 val_452 -453 val_453 453 val_453 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -455 val_455 455 val_455 -457 val_457 457 val_457 -458 val_458 458 val_458 -458 val_458 458 val_458 -458 val_458 458 val_458 -458 val_458 458 val_458 -459 val_459 459 val_459 -459 val_459 459 val_459 -459 val_459 459 val_459 -459 val_459 459 val_459 -460 val_460 460 val_460 -462 val_462 462 val_462 -462 val_462 462 val_462 -462 val_462 462 val_462 -462 val_462 462 val_462 -463 val_463 463 val_463 -463 val_463 463 val_463 -463 val_463 463 val_463 -463 val_463 463 val_463 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -467 val_467 467 val_467 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -470 val_470 470 val_470 -472 val_472 472 val_472 -475 val_475 475 val_475 -477 val_477 477 val_477 -478 val_478 478 val_478 -478 val_478 478 val_478 -478 val_478 478 val_478 -478 val_478 478 val_478 -479 val_479 479 val_479 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -481 val_481 481 val_481 -482 val_482 482 val_482 -483 val_483 483 val_483 -484 val_484 484 val_484 -485 val_485 485 val_485 -487 val_487 487 val_487 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -490 val_490 490 val_490 -491 val_491 491 val_491 -492 val_492 492 val_492 -492 val_492 492 val_492 -492 val_492 492 val_492 -492 val_492 492 val_492 -493 val_493 493 val_493 -494 val_494 494 val_494 -495 val_495 495 val_495 -496 val_496 496 val_496 -497 val_497 497 val_497 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -PREHOOK: query: insert overwrite table normal_join_results_n0 select * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@normal_join_results_n0 -POSTHOOK: query: insert overwrite table normal_join_results_n0 select * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@normal_join_results_n0 -POSTHOOK: Lineage: normal_join_results_n0.k1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: normal_join_results_n0.k2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: normal_join_results_n0.v1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: normal_join_results_n0.v2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from normal_join_results_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@normal_join_results_n0 -#### A masked pattern was here #### -POSTHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from normal_join_results_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@normal_join_results_n0 -#### A masked pattern was here #### -278697 278697 101852390308 101852390308 -PREHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from smb_join_results_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -POSTHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from smb_join_results_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -278697 278697 101852390308 101852390308 -PREHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, v1, k2, v2 - Column Types: int, string, int, string - Table: default.smb_join_results_n0 - -PREHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -POSTHOOK: Lineage: smb_join_results_n0.k1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.k2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -POSTHOOK: Lineage: smb_join_results_n0.k1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.k2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select * from smb_join_results_n0 order by k1 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * from smb_join_results_n0 order by k1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -2 val_2 2 val_2 -4 val_4 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -8 val_8 8 val_8 -9 val_9 9 val_9 -10 val_10 10 val_10 -11 val_11 11 val_11 -12 val_12 12 val_12 -12 val_12 12 val_12 -12 val_12 12 val_12 -12 val_12 12 val_12 -15 val_15 15 val_15 -15 val_15 15 val_15 -15 val_15 15 val_15 -15 val_15 15 val_15 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -20 val_20 20 val_20 -24 val_24 24 val_24 -24 val_24 24 val_24 -24 val_24 24 val_24 -24 val_24 24 val_24 -26 val_26 26 val_26 -26 val_26 26 val_26 -26 val_26 26 val_26 -26 val_26 26 val_26 -27 val_27 27 val_27 -28 val_28 28 val_28 -30 val_30 30 val_30 -33 val_33 33 val_33 -34 val_34 34 val_34 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -35 val_35 35 val_35 -37 val_37 37 val_37 -37 val_37 37 val_37 -37 val_37 37 val_37 -37 val_37 37 val_37 -41 val_41 41 val_41 -42 val_42 42 val_42 -42 val_42 42 val_42 -42 val_42 42 val_42 -42 val_42 42 val_42 -43 val_43 43 val_43 -44 val_44 44 val_44 -47 val_47 47 val_47 -51 val_51 51 val_51 -51 val_51 51 val_51 -51 val_51 51 val_51 -51 val_51 51 val_51 -53 val_53 53 val_53 -54 val_54 54 val_54 -57 val_57 57 val_57 -58 val_58 58 val_58 -58 val_58 58 val_58 -58 val_58 58 val_58 -58 val_58 58 val_58 -64 val_64 64 val_64 -65 val_65 65 val_65 -66 val_66 66 val_66 -67 val_67 67 val_67 -67 val_67 67 val_67 -67 val_67 67 val_67 -67 val_67 67 val_67 -69 val_69 69 val_69 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -70 val_70 70 val_70 -72 val_72 72 val_72 -72 val_72 72 val_72 -72 val_72 72 val_72 -72 val_72 72 val_72 -74 val_74 74 val_74 -76 val_76 76 val_76 -76 val_76 76 val_76 -76 val_76 76 val_76 -76 val_76 76 val_76 -77 val_77 77 val_77 -78 val_78 78 val_78 -80 val_80 80 val_80 -82 val_82 82 val_82 -83 val_83 83 val_83 -83 val_83 83 val_83 -83 val_83 83 val_83 -83 val_83 83 val_83 -84 val_84 84 val_84 -84 val_84 84 val_84 -84 val_84 84 val_84 -84 val_84 84 val_84 -85 val_85 85 val_85 -86 val_86 86 val_86 -87 val_87 87 val_87 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -90 val_90 90 val_90 -92 val_92 92 val_92 -95 val_95 95 val_95 -95 val_95 95 val_95 -95 val_95 95 val_95 -95 val_95 95 val_95 -96 val_96 96 val_96 -97 val_97 97 val_97 -97 val_97 97 val_97 -97 val_97 97 val_97 -97 val_97 97 val_97 -98 val_98 98 val_98 -98 val_98 98 val_98 -98 val_98 98 val_98 -98 val_98 98 val_98 -100 val_100 100 val_100 -100 val_100 100 val_100 -100 val_100 100 val_100 -100 val_100 100 val_100 -103 val_103 103 val_103 -103 val_103 103 val_103 -103 val_103 103 val_103 -103 val_103 103 val_103 -104 val_104 104 val_104 -104 val_104 104 val_104 -104 val_104 104 val_104 -104 val_104 104 val_104 -105 val_105 105 val_105 -111 val_111 111 val_111 -113 val_113 113 val_113 -113 val_113 113 val_113 -113 val_113 113 val_113 -113 val_113 113 val_113 -114 val_114 114 val_114 -116 val_116 116 val_116 -118 val_118 118 val_118 -118 val_118 118 val_118 -118 val_118 118 val_118 -118 val_118 118 val_118 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -119 val_119 119 val_119 -120 val_120 120 val_120 -120 val_120 120 val_120 -120 val_120 120 val_120 -120 val_120 120 val_120 -125 val_125 125 val_125 -125 val_125 125 val_125 -125 val_125 125 val_125 -125 val_125 125 val_125 -126 val_126 126 val_126 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -128 val_128 128 val_128 -129 val_129 129 val_129 -129 val_129 129 val_129 -129 val_129 129 val_129 -129 val_129 129 val_129 -131 val_131 131 val_131 -133 val_133 133 val_133 -134 val_134 134 val_134 -134 val_134 134 val_134 -134 val_134 134 val_134 -134 val_134 134 val_134 -136 val_136 136 val_136 -137 val_137 137 val_137 -137 val_137 137 val_137 -137 val_137 137 val_137 -137 val_137 137 val_137 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -138 val_138 138 val_138 -143 val_143 143 val_143 -145 val_145 145 val_145 -146 val_146 146 val_146 -146 val_146 146 val_146 -146 val_146 146 val_146 -146 val_146 146 val_146 -149 val_149 149 val_149 -149 val_149 149 val_149 -149 val_149 149 val_149 -149 val_149 149 val_149 -150 val_150 150 val_150 -152 val_152 152 val_152 -152 val_152 152 val_152 -152 val_152 152 val_152 -152 val_152 152 val_152 -153 val_153 153 val_153 -155 val_155 155 val_155 -156 val_156 156 val_156 -157 val_157 157 val_157 -158 val_158 158 val_158 -160 val_160 160 val_160 -162 val_162 162 val_162 -163 val_163 163 val_163 -164 val_164 164 val_164 -164 val_164 164 val_164 -164 val_164 164 val_164 -164 val_164 164 val_164 -165 val_165 165 val_165 -165 val_165 165 val_165 -165 val_165 165 val_165 -165 val_165 165 val_165 -166 val_166 166 val_166 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -167 val_167 167 val_167 -168 val_168 168 val_168 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -169 val_169 169 val_169 -170 val_170 170 val_170 -172 val_172 172 val_172 -172 val_172 172 val_172 -172 val_172 172 val_172 -172 val_172 172 val_172 -174 val_174 174 val_174 -174 val_174 174 val_174 -174 val_174 174 val_174 -174 val_174 174 val_174 -175 val_175 175 val_175 -175 val_175 175 val_175 -175 val_175 175 val_175 -175 val_175 175 val_175 -176 val_176 176 val_176 -176 val_176 176 val_176 -176 val_176 176 val_176 -176 val_176 176 val_176 -177 val_177 177 val_177 -178 val_178 178 val_178 -179 val_179 179 val_179 -179 val_179 179 val_179 -179 val_179 179 val_179 -179 val_179 179 val_179 -180 val_180 180 val_180 -181 val_181 181 val_181 -183 val_183 183 val_183 -186 val_186 186 val_186 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -187 val_187 187 val_187 -189 val_189 189 val_189 -190 val_190 190 val_190 -191 val_191 191 val_191 -191 val_191 191 val_191 -191 val_191 191 val_191 -191 val_191 191 val_191 -192 val_192 192 val_192 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -193 val_193 193 val_193 -194 val_194 194 val_194 -195 val_195 195 val_195 -195 val_195 195 val_195 -195 val_195 195 val_195 -195 val_195 195 val_195 -196 val_196 196 val_196 -197 val_197 197 val_197 -197 val_197 197 val_197 -197 val_197 197 val_197 -197 val_197 197 val_197 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -199 val_199 199 val_199 -200 val_200 200 val_200 -200 val_200 200 val_200 -200 val_200 200 val_200 -200 val_200 200 val_200 -201 val_201 201 val_201 -202 val_202 202 val_202 -203 val_203 203 val_203 -203 val_203 203 val_203 -203 val_203 203 val_203 -203 val_203 203 val_203 -205 val_205 205 val_205 -205 val_205 205 val_205 -205 val_205 205 val_205 -205 val_205 205 val_205 -207 val_207 207 val_207 -207 val_207 207 val_207 -207 val_207 207 val_207 -207 val_207 207 val_207 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -208 val_208 208 val_208 -209 val_209 209 val_209 -209 val_209 209 val_209 -209 val_209 209 val_209 -209 val_209 209 val_209 -213 val_213 213 val_213 -213 val_213 213 val_213 -213 val_213 213 val_213 -213 val_213 213 val_213 -214 val_214 214 val_214 -216 val_216 216 val_216 -216 val_216 216 val_216 -216 val_216 216 val_216 -216 val_216 216 val_216 -217 val_217 217 val_217 -217 val_217 217 val_217 -217 val_217 217 val_217 -217 val_217 217 val_217 -218 val_218 218 val_218 -219 val_219 219 val_219 -219 val_219 219 val_219 -219 val_219 219 val_219 -219 val_219 219 val_219 -221 val_221 221 val_221 -221 val_221 221 val_221 -221 val_221 221 val_221 -221 val_221 221 val_221 -222 val_222 222 val_222 -223 val_223 223 val_223 -223 val_223 223 val_223 -223 val_223 223 val_223 -223 val_223 223 val_223 -224 val_224 224 val_224 -224 val_224 224 val_224 -224 val_224 224 val_224 -224 val_224 224 val_224 -226 val_226 226 val_226 -228 val_228 228 val_228 -229 val_229 229 val_229 -229 val_229 229 val_229 -229 val_229 229 val_229 -229 val_229 229 val_229 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -230 val_230 230 val_230 -233 val_233 233 val_233 -233 val_233 233 val_233 -233 val_233 233 val_233 -233 val_233 233 val_233 -235 val_235 235 val_235 -237 val_237 237 val_237 -237 val_237 237 val_237 -237 val_237 237 val_237 -237 val_237 237 val_237 -238 val_238 238 val_238 -238 val_238 238 val_238 -238 val_238 238 val_238 -238 val_238 238 val_238 -239 val_239 239 val_239 -239 val_239 239 val_239 -239 val_239 239 val_239 -239 val_239 239 val_239 -241 val_241 241 val_241 -242 val_242 242 val_242 -242 val_242 242 val_242 -242 val_242 242 val_242 -242 val_242 242 val_242 -244 val_244 244 val_244 -247 val_247 247 val_247 -248 val_248 248 val_248 -249 val_249 249 val_249 -252 val_252 252 val_252 -255 val_255 255 val_255 -255 val_255 255 val_255 -255 val_255 255 val_255 -255 val_255 255 val_255 -256 val_256 256 val_256 -256 val_256 256 val_256 -256 val_256 256 val_256 -256 val_256 256 val_256 -257 val_257 257 val_257 -258 val_258 258 val_258 -260 val_260 260 val_260 -262 val_262 262 val_262 -263 val_263 263 val_263 -265 val_265 265 val_265 -265 val_265 265 val_265 -265 val_265 265 val_265 -265 val_265 265 val_265 -266 val_266 266 val_266 -272 val_272 272 val_272 -272 val_272 272 val_272 -272 val_272 272 val_272 -272 val_272 272 val_272 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -273 val_273 273 val_273 -274 val_274 274 val_274 -275 val_275 275 val_275 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -277 val_277 277 val_277 -278 val_278 278 val_278 -278 val_278 278 val_278 -278 val_278 278 val_278 -278 val_278 278 val_278 -280 val_280 280 val_280 -280 val_280 280 val_280 -280 val_280 280 val_280 -280 val_280 280 val_280 -281 val_281 281 val_281 -281 val_281 281 val_281 -281 val_281 281 val_281 -281 val_281 281 val_281 -282 val_282 282 val_282 -282 val_282 282 val_282 -282 val_282 282 val_282 -282 val_282 282 val_282 -283 val_283 283 val_283 -284 val_284 284 val_284 -285 val_285 285 val_285 -286 val_286 286 val_286 -287 val_287 287 val_287 -288 val_288 288 val_288 -288 val_288 288 val_288 -288 val_288 288 val_288 -288 val_288 288 val_288 -289 val_289 289 val_289 -291 val_291 291 val_291 -292 val_292 292 val_292 -296 val_296 296 val_296 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -298 val_298 298 val_298 -302 val_302 302 val_302 -305 val_305 305 val_305 -306 val_306 306 val_306 -307 val_307 307 val_307 -307 val_307 307 val_307 -307 val_307 307 val_307 -307 val_307 307 val_307 -308 val_308 308 val_308 -309 val_309 309 val_309 -309 val_309 309 val_309 -309 val_309 309 val_309 -309 val_309 309 val_309 -310 val_310 310 val_310 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -311 val_311 311 val_311 -315 val_315 315 val_315 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -316 val_316 316 val_316 -317 val_317 317 val_317 -317 val_317 317 val_317 -317 val_317 317 val_317 -317 val_317 317 val_317 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -318 val_318 318 val_318 -321 val_321 321 val_321 -321 val_321 321 val_321 -321 val_321 321 val_321 -321 val_321 321 val_321 -322 val_322 322 val_322 -322 val_322 322 val_322 -322 val_322 322 val_322 -322 val_322 322 val_322 -323 val_323 323 val_323 -325 val_325 325 val_325 -325 val_325 325 val_325 -325 val_325 325 val_325 -325 val_325 325 val_325 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -327 val_327 327 val_327 -331 val_331 331 val_331 -331 val_331 331 val_331 -331 val_331 331 val_331 -331 val_331 331 val_331 -332 val_332 332 val_332 -333 val_333 333 val_333 -333 val_333 333 val_333 -333 val_333 333 val_333 -333 val_333 333 val_333 -335 val_335 335 val_335 -336 val_336 336 val_336 -338 val_338 338 val_338 -339 val_339 339 val_339 -341 val_341 341 val_341 -342 val_342 342 val_342 -342 val_342 342 val_342 -342 val_342 342 val_342 -342 val_342 342 val_342 -344 val_344 344 val_344 -344 val_344 344 val_344 -344 val_344 344 val_344 -344 val_344 344 val_344 -345 val_345 345 val_345 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -348 val_348 348 val_348 -351 val_351 351 val_351 -353 val_353 353 val_353 -353 val_353 353 val_353 -353 val_353 353 val_353 -353 val_353 353 val_353 -356 val_356 356 val_356 -360 val_360 360 val_360 -362 val_362 362 val_362 -364 val_364 364 val_364 -365 val_365 365 val_365 -366 val_366 366 val_366 -367 val_367 367 val_367 -367 val_367 367 val_367 -367 val_367 367 val_367 -367 val_367 367 val_367 -368 val_368 368 val_368 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -369 val_369 369 val_369 -373 val_373 373 val_373 -374 val_374 374 val_374 -375 val_375 375 val_375 -377 val_377 377 val_377 -378 val_378 378 val_378 -379 val_379 379 val_379 -382 val_382 382 val_382 -382 val_382 382 val_382 -382 val_382 382 val_382 -382 val_382 382 val_382 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -384 val_384 384 val_384 -386 val_386 386 val_386 -389 val_389 389 val_389 -392 val_392 392 val_392 -393 val_393 393 val_393 -394 val_394 394 val_394 -395 val_395 395 val_395 -395 val_395 395 val_395 -395 val_395 395 val_395 -395 val_395 395 val_395 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -396 val_396 396 val_396 -397 val_397 397 val_397 -397 val_397 397 val_397 -397 val_397 397 val_397 -397 val_397 397 val_397 -399 val_399 399 val_399 -399 val_399 399 val_399 -399 val_399 399 val_399 -399 val_399 399 val_399 -400 val_400 400 val_400 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -401 val_401 401 val_401 -402 val_402 402 val_402 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -403 val_403 403 val_403 -404 val_404 404 val_404 -404 val_404 404 val_404 -404 val_404 404 val_404 -404 val_404 404 val_404 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -406 val_406 406 val_406 -407 val_407 407 val_407 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -409 val_409 409 val_409 -411 val_411 411 val_411 -413 val_413 413 val_413 -413 val_413 413 val_413 -413 val_413 413 val_413 -413 val_413 413 val_413 -414 val_414 414 val_414 -414 val_414 414 val_414 -414 val_414 414 val_414 -414 val_414 414 val_414 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -417 val_417 417 val_417 -418 val_418 418 val_418 -419 val_419 419 val_419 -421 val_421 421 val_421 -424 val_424 424 val_424 -424 val_424 424 val_424 -424 val_424 424 val_424 -424 val_424 424 val_424 -427 val_427 427 val_427 -429 val_429 429 val_429 -429 val_429 429 val_429 -429 val_429 429 val_429 -429 val_429 429 val_429 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -430 val_430 430 val_430 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -431 val_431 431 val_431 -432 val_432 432 val_432 -435 val_435 435 val_435 -436 val_436 436 val_436 -437 val_437 437 val_437 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -438 val_438 438 val_438 -439 val_439 439 val_439 -439 val_439 439 val_439 -439 val_439 439 val_439 -439 val_439 439 val_439 -443 val_443 443 val_443 -444 val_444 444 val_444 -446 val_446 446 val_446 -448 val_448 448 val_448 -449 val_449 449 val_449 -452 val_452 452 val_452 -453 val_453 453 val_453 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -454 val_454 454 val_454 -455 val_455 455 val_455 -457 val_457 457 val_457 -458 val_458 458 val_458 -458 val_458 458 val_458 -458 val_458 458 val_458 -458 val_458 458 val_458 -459 val_459 459 val_459 -459 val_459 459 val_459 -459 val_459 459 val_459 -459 val_459 459 val_459 -460 val_460 460 val_460 -462 val_462 462 val_462 -462 val_462 462 val_462 -462 val_462 462 val_462 -462 val_462 462 val_462 -463 val_463 463 val_463 -463 val_463 463 val_463 -463 val_463 463 val_463 -463 val_463 463 val_463 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -466 val_466 466 val_466 -467 val_467 467 val_467 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -468 val_468 468 val_468 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -469 val_469 469 val_469 -470 val_470 470 val_470 -472 val_472 472 val_472 -475 val_475 475 val_475 -477 val_477 477 val_477 -478 val_478 478 val_478 -478 val_478 478 val_478 -478 val_478 478 val_478 -478 val_478 478 val_478 -479 val_479 479 val_479 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -480 val_480 480 val_480 -481 val_481 481 val_481 -482 val_482 482 val_482 -483 val_483 483 val_483 -484 val_484 484 val_484 -485 val_485 485 val_485 -487 val_487 487 val_487 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -489 val_489 489 val_489 -490 val_490 490 val_490 -491 val_491 491 val_491 -492 val_492 492 val_492 -492 val_492 492 val_492 -492 val_492 492 val_492 -492 val_492 492 val_492 -493 val_493 493 val_493 -494 val_494 494 val_494 -495 val_495 495 val_495 -496 val_496 496 val_496 -497 val_497 497 val_497 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -498 val_498 498 val_498 -PREHOOK: query: insert overwrite table normal_join_results_n0 select * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@normal_join_results_n0 -POSTHOOK: query: insert overwrite table normal_join_results_n0 select * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@normal_join_results_n0 -POSTHOOK: Lineage: normal_join_results_n0.k1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: normal_join_results_n0.k2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: normal_join_results_n0.v1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: normal_join_results_n0.v2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from normal_join_results_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@normal_join_results_n0 -#### A masked pattern was here #### -POSTHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from normal_join_results_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@normal_join_results_n0 -#### A masked pattern was here #### -278697 278697 101852390308 101852390308 -PREHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from smb_join_results_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -POSTHOOK: query: select sum(hash(k1)) as k1, sum(hash(k2)) as k2, sum(hash(v1)) as v1, sum(hash(v2)) as v2 from smb_join_results_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_join_results_n0 -#### A masked pattern was here #### -278697 278697 101852390308 101852390308 -PREHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key > 1000) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > 1000) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key > 1000) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > 1000) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - minReductionHashAggr: 0.0 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, v1, k2, v2 - Column Types: int, string, int, string - Table: default.smb_join_results_n0 - -PREHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(a)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -POSTHOOK: Lineage: smb_join_results_n0.k1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.k2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: explain -insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key > 1000) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > 1000) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key > 1000) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > 1000) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - minReductionHashAggr: 0.0 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: llap - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.smb_join_results_n0 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, v1, k2, v2 - Column Types: int, string, int, string - Table: default.smb_join_results_n0 - -PREHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -PREHOOK: Output: default@smb_join_results_n0 -POSTHOOK: query: insert overwrite table smb_join_results_n0 -select /*+mapjoin(b)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key where a.key>1000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -POSTHOOK: Output: default@smb_join_results_n0 -POSTHOOK: Lineage: smb_join_results_n0.k1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.k2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v1 SIMPLE [(smb_bucket4_1_n0)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: smb_join_results_n0.v2 SIMPLE [(smb_bucket4_2_n0)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: explain -select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key join smb_bucket4_2_n0 c on b.key = c.key where a.key>1000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain -select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key join smb_bucket4_2_n0 c on b.key = c.key where a.key>1000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: b - filterExpr: (key > 1000) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > 1000) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Dummy Store - Map Operator Tree: - TableScan - alias: a - filterExpr: (key > 1000) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > 1000) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - Execution mode: llap - Map 4 - Map Operator Tree: - TableScan - alias: c - filterExpr: (key > 1000) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > 1000) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key join smb_bucket4_2_n0 c on b.key = c.key where a.key>1000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n0 -PREHOOK: Input: default@smb_bucket4_2_n0 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n0 a join smb_bucket4_2_n0 b on a.key = b.key join smb_bucket4_2_n0 c on b.key = c.key where a.key>1000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n0 -POSTHOOK: Input: default@smb_bucket4_2_n0 -#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/llap/smb_mapjoin_8.q.out ql/src/test/results/clientpositive/llap/smb_mapjoin_8.q.out deleted file mode 100644 index 26b7eb98b7..0000000000 --- ql/src/test/results/clientpositive/llap/smb_mapjoin_8.q.out +++ /dev/null @@ -1,464 +0,0 @@ -PREHOOK: query: create table smb_bucket_input (key int, value string) stored as rcfile -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket_input -POSTHOOK: query: create table smb_bucket_input (key int, value string) stored as rcfile -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket_input -PREHOOK: query: load data local inpath '../../data/files/smb_bucket_input.rc' into table smb_bucket_input -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@smb_bucket_input -POSTHOOK: query: load data local inpath '../../data/files/smb_bucket_input.rc' into table smb_bucket_input -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@smb_bucket_input -PREHOOK: query: CREATE TABLE smb_bucket4_1_n1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: CREATE TABLE smb_bucket4_1_n1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket4_1_n1 -PREHOOK: query: CREATE TABLE smb_bucket4_2_n1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: CREATE TABLE smb_bucket4_2_n1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket4_2_n1 -PREHOOK: query: CREATE TABLE smb_bucket4_3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@smb_bucket4_3 -POSTHOOK: query: CREATE TABLE smb_bucket4_3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@smb_bucket4_3 -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=4 or key=2000 or key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=4 or key=2000 or key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=484 or key=3000 or key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=484 or key=3000 or key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -2000 val_169 NULL NULL -4 val_356 NULL NULL -4000 val_125 NULL NULL -NULL NULL 3000 val_169 -NULL NULL 484 val_169 -NULL NULL 5000 val_125 -PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -2000 val_169 NULL NULL -4 val_356 NULL NULL -4000 val_125 NULL NULL -NULL NULL 3000 val_169 -NULL NULL 484 val_169 -NULL NULL 5000 val_125 -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=2000 or key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=2000 or key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=3000 or key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=3000 or key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -2000 val_169 NULL NULL -4000 val_125 NULL NULL -NULL NULL 3000 val_169 -NULL NULL 5000 val_125 -PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -2000 val_169 NULL NULL -4000 val_125 NULL NULL -NULL NULL 3000 val_169 -NULL NULL 5000 val_125 -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -4000 val_125 NULL NULL -NULL NULL 5000 val_125 -PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -4000 val_125 NULL NULL -NULL NULL 5000 val_125 -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 or key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 or key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=1000 or key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=1000 or key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -1000 val_1000 1000 val_1000 -4000 val_125 NULL NULL -NULL NULL 5000 val_125 -PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -#### A masked pattern was here #### -1000 val_1000 1000 val_1000 -4000 val_125 NULL NULL -NULL NULL 5000 val_125 -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 or key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 or key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=1000 or key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=1000 or key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=1000 or key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_3 -POSTHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=1000 or key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_3 -POSTHOOK: Lineage: smb_bucket4_3.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_3.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -PREHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -POSTHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -1000 val_1000 1000 val_1000 1000 val_1000 -4000 val_125 NULL NULL NULL NULL -NULL NULL 5000 val_125 NULL NULL -NULL NULL NULL NULL 5000 val_125 -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 or key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 or key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=1000 or key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=1000 or key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=1000 or key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_3 -POSTHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=1000 or key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_3 -POSTHOOK: Lineage: smb_bucket4_3.key SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: smb_bucket4_3.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -PREHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -POSTHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -1000 val_1000 1000 val_1000 1000 val_1000 -4000 val_125 NULL NULL 4000 val_125 -NULL NULL 5000 val_125 NULL NULL -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_3 -POSTHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_3 -POSTHOOK: Lineage: smb_bucket4_3.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_3.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -PREHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -POSTHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -4000 val_125 NULL NULL 4000 val_125 -NULL NULL 5000 val_125 NULL NULL -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=00000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=00000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_3 -POSTHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_3 -POSTHOOK: Lineage: smb_bucket4_3.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_3.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -PREHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -POSTHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -NULL NULL 4000 val_125 NULL NULL -NULL NULL NULL NULL 5000 val_125 -PREHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_1_n1 select * from smb_bucket_input where key=1000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_1_n1 -POSTHOOK: Lineage: smb_bucket4_1_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_1_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=4000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: query: insert overwrite table smb_bucket4_2_n1 select * from smb_bucket_input where key=4000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_2_n1 -POSTHOOK: Lineage: smb_bucket4_2_n1.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_2_n1.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=5000 -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket_input -PREHOOK: Output: default@smb_bucket4_3 -POSTHOOK: query: insert overwrite table smb_bucket4_3 select * from smb_bucket_input where key=5000 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket_input -POSTHOOK: Output: default@smb_bucket4_3 -POSTHOOK: Lineage: smb_bucket4_3.key SIMPLE [] -POSTHOOK: Lineage: smb_bucket4_3.value SIMPLE [(smb_bucket_input)smb_bucket_input.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@smb_bucket4_1_n1 -PREHOOK: Input: default@smb_bucket4_2_n1 -PREHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -POSTHOOK: query: select /*+mapjoin(b,c)*/ * from smb_bucket4_1_n1 a full outer join smb_bucket4_2_n1 b on a.key = b.key -full outer join smb_bucket4_3 c on a.key=c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@smb_bucket4_1_n1 -POSTHOOK: Input: default@smb_bucket4_2_n1 -POSTHOOK: Input: default@smb_bucket4_3 -#### A masked pattern was here #### -1000 val_1000 NULL NULL NULL NULL -NULL NULL 4000 val_125 NULL NULL -NULL NULL NULL NULL 5000 val_125 diff --git ql/src/test/results/clientpositive/sort.q.out ql/src/test/results/clientpositive/llap/sort.q.out similarity index 78% rename from ql/src/test/results/clientpositive/sort.q.out rename to ql/src/test/results/clientpositive/llap/sort.q.out index 8c11f0f940..7cfa945250 100644 --- ql/src/test/results/clientpositive/sort.q.out +++ ql/src/test/results/clientpositive/llap/sort.q.out @@ -14,34 +14,43 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -573,34 +582,43 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/source.q.out ql/src/test/results/clientpositive/llap/source.q.out similarity index 97% rename from ql/src/test/results/clientpositive/source.q.out rename to ql/src/test/results/clientpositive/llap/source.q.out index 00307e9c0e..83a7934750 100644 --- ql/src/test/results/clientpositive/source.q.out +++ ql/src/test/results/clientpositive/llap/source.q.out @@ -18,11 +18,9 @@ STAGE PLANS: Processor Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRC x @@ -553,11 +551,9 @@ STAGE PLANS: Processor Tree: TableScan alias: x - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT x.* FROM SRC x diff --git ql/src/test/results/clientpositive/llap/stat_estimate_drill.q.out ql/src/test/results/clientpositive/llap/stat_estimate_drill.q.out new file mode 100644 index 0000000000..4110e7efa6 --- /dev/null +++ ql/src/test/results/clientpositive/llap/stat_estimate_drill.q.out @@ -0,0 +1,355 @@ +PREHOOK: query: drop table if exists t1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists t1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table if exists t8 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists t8 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table t1 (a integer) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t1 +POSTHOOK: query: create table t1 (a integer) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1 +PREHOOK: query: create table t3 (a integer,b integer,c integer) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t3 +POSTHOOK: query: create table t3 (a integer,b integer,c integer) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t3 +PREHOOK: query: insert into t1 values (1),(2),(3),(4),(5),(6),(7),(8),(9),(0) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t1 +POSTHOOK: query: insert into t1 values (1),(2),(3),(4),(5),(6),(7),(8),(9),(0) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t1 +POSTHOOK: Lineage: t1.a SCRIPT [] +Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: insert into t3 + select x1.a as a,x2.a as b,x3.a as c from + t1 x1 + join t1 x2 + join t1 x3 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Output: default@t3 +POSTHOOK: query: insert into t3 + select x1.a as a,x2.a as b,x3.a as c from + t1 x1 + join t1 x2 + join t1 x3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Output: default@t3 +POSTHOOK: Lineage: t3.a SIMPLE [(t1)x1.FieldSchema(name:a, type:int, comment:null), ] +POSTHOOK: Lineage: t3.b SIMPLE [(t1)x2.FieldSchema(name:a, type:int, comment:null), ] +POSTHOOK: Lineage: t3.c SIMPLE [(t1)x3.FieldSchema(name:a, type:int, comment:null), ] +PREHOOK: query: analyze table t3 compute statistics for columns +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@t3 +PREHOOK: Output: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: analyze table t3 compute statistics for columns +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@t3 +POSTHOOK: Output: default@t3 +#### A masked pattern was here #### +PREHOOK: query: select sum(a) from t3 where b in (2,3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where b in (2,3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where b in (2,3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t3 where b in (2,3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_14] + Select Operator [SEL_13] (rows=2/2 width=8) + Output:["_col0"] + Group By Operator [GBY_12] (rows=2/2 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_11] + PartitionCols:_col0 + Group By Operator [GBY_10] (rows=2/2 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:b + Filter Operator [FIL_9] (rows=200/200 width=8) + predicate:(b) IN (2, 3) + TableScan [TS_0] (rows=1000/1000 width=8) + default@t3,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t3 where a=1 or a=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 or a=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 or a=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 or a=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_14] + Select Operator [SEL_13] (rows=10/10 width=8) + Output:["_col0"] + Group By Operator [GBY_12] (rows=10/10 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_11] + PartitionCols:_col0 + Group By Operator [GBY_10] (rows=10/10 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:b + Filter Operator [FIL_9] (rows=200/200 width=8) + predicate:(a) IN (1, 2) + TableScan [TS_0] (rows=1000/1000 width=8) + default@t3,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_14] + Select Operator [SEL_13] (rows=10/10 width=8) + Output:["_col0"] + Group By Operator [GBY_12] (rows=10/10 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_11] + PartitionCols:_col0 + Group By Operator [GBY_10] (rows=10/10 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:b + Filter Operator [FIL_9] (rows=110/110 width=8) + predicate:((a = 1) or ((a = 2) and (b = 3))) + TableScan [TS_0] (rows=1000/1000 width=8) + default@t3,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t3 where a=1 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_16] + Select Operator [SEL_15] (rows=10/10 width=8) + Output:["_col0"] + Group By Operator [GBY_14] (rows=10/10 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_13] + PartitionCols:_col0 + Group By Operator [GBY_12] (rows=10/10 width=12) + Output:["_col0","_col1"],aggregations:["sum(1)"],keys:_col0 + Select Operator [SEL_11] (rows=100/100 width=8) + Output:["_col0"] + Filter Operator [FIL_10] (rows=100/100 width=8) + predicate:(a = 1) + TableScan [TS_0] (rows=1000/1000 width=8) + default@t3,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t3 where a=1 and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_16] + Select Operator [SEL_15] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_14] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_13] + PartitionCols:_col0 + Group By Operator [GBY_12] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(1)"],keys:true + Select Operator [SEL_11] (rows=10/10 width=8) + Filter Operator [FIL_10] (rows=10/10 width=8) + predicate:((a = 1) and (b = 2)) + TableScan [TS_0] (rows=1000/1000 width=8) + default@t3,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t3 where a=1 and b=2 and c=3 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 and b=2 and c=3 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 and c=3 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 and c=3 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_16] + Select Operator [SEL_15] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_14] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_13] + PartitionCols:_col0 + Group By Operator [GBY_12] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(1)"],keys:true + Select Operator [SEL_11] (rows=1/1 width=12) + Filter Operator [FIL_10] (rows=1/1 width=12) + predicate:((a = 1) and (b = 2) and (c = 3)) + TableScan [TS_0] (rows=1000/1000 width=12) + default@t3,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b","c"] + +PREHOOK: query: select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_14] + Select Operator [SEL_13] (rows=10/3 width=8) + Output:["_col0"] + Group By Operator [GBY_12] (rows=10/3 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_11] + PartitionCols:_col0 + Group By Operator [GBY_10] (rows=10/3 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:b + Filter Operator [FIL_9] (rows=30/30 width=8) + predicate:(struct(a,b)) IN (const struct(1,2), const struct(2,3), const struct(3,4)) + TableScan [TS_0] (rows=1000/1000 width=8) + default@t3,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + diff --git ql/src/test/results/clientpositive/llap/stat_estimate_related_col.q.out ql/src/test/results/clientpositive/llap/stat_estimate_related_col.q.out new file mode 100644 index 0000000000..2125185507 --- /dev/null +++ ql/src/test/results/clientpositive/llap/stat_estimate_related_col.q.out @@ -0,0 +1,500 @@ +PREHOOK: query: drop table if exists t1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists t1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table if exists t8 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists t8 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table t1 (a integer,b integer) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t1 +POSTHOOK: query: create table t1 (a integer,b integer) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1 +PREHOOK: query: create table t8 like t1 +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t8 +POSTHOOK: query: create table t8 like t1 +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t8 +PREHOOK: query: insert into t1 values (1,1),(2,2),(3,3),(4,4),(5,5) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t1 +POSTHOOK: query: insert into t1 values (1,1),(2,2),(3,3),(4,4),(5,5) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t1 +POSTHOOK: Lineage: t1.a SCRIPT [] +POSTHOOK: Lineage: t1.b SCRIPT [] +PREHOOK: query: insert into t8 +select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 union all +select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Output: default@t8 +POSTHOOK: query: insert into t8 +select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 union all +select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Output: default@t8 +POSTHOOK: Lineage: t8.a EXPRESSION [(t1)t1.FieldSchema(name:a, type:int, comment:null), ] +POSTHOOK: Lineage: t8.b EXPRESSION [(t1)t1.FieldSchema(name:b, type:int, comment:null), ] +PREHOOK: query: analyze table t1 compute statistics for columns +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@t1 +PREHOOK: Output: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: analyze table t1 compute statistics for columns +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@t1 +POSTHOOK: Output: default@t1 +#### A masked pattern was here #### +PREHOOK: query: analyze table t8 compute statistics for columns +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@t8 +PREHOOK: Output: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: analyze table t8 compute statistics for columns +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@t8 +POSTHOOK: Output: default@t8 +#### A masked pattern was here #### +PREHOOK: query: select sum(a) from t8 where b in (2,3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t8 where b in (2,3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_14] + Select Operator [SEL_13] (rows=2/2 width=8) + Output:["_col0"] + Group By Operator [GBY_12] (rows=2/2 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_11] + PartitionCols:_col0 + Group By Operator [GBY_10] (rows=2/2 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:b + Filter Operator [FIL_9] (rows=16/16 width=8) + predicate:(b) IN (2, 3) + TableScan [TS_0] (rows=40/40 width=8) + default@t8,t8,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t8 where b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t8 where b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t8 where b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t8 where b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=8/8 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=8/8 width=8) + predicate:(b = 2) + TableScan [TS_0] (rows=40/40 width=8) + default@t8,t8,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t1 where 2=b and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t1 where 2=b and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t1 where 2=b and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t1 where 2=b and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=1/1 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=1/1 width=8) + predicate:((2 = b) and (b = 2)) + TableScan [TS_0] (rows=5/5 width=8) + default@t1,t1,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t1 where b in (2,3) and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t1 where b in (2,3) and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t1 where b in (2,3) and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t1 where b in (2,3) and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=1/1 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=1/1 width=8) + predicate:((b) IN (2, 3) and (b = 2)) + TableScan [TS_0] (rows=5/5 width=8) + default@t1,t1,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t8 where b in (2,3) and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t8 where b in (2,3) and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=8/8 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=8/8 width=8) + predicate:((b) IN (2, 3) and (b = 2)) + TableScan [TS_0] (rows=40/40 width=8) + default@t8,t8,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 3 vectorized, llap + File Output Operator [FS_25] + Group By Operator [GBY_24] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count(VALUE._col0)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap + PARTITION_ONLY_SHUFFLE [RS_10] + Group By Operator [GBY_9] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count()"] + Merge Join Operator [MERGEJOIN_19] (rows=64/64 width=8) + Conds:RS_21.3=RS_23.3(Inner) + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_21] + PartitionCols:3 + Filter Operator [FIL_20] (rows=8/8 width=4) + predicate:(a = 3) + TableScan [TS_0] (rows=40/40 width=4) + default@t8,ta,Tbl:COMPLETE,Col:COMPLETE,Output:["a"] + <-Map 4 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_23] + PartitionCols:3 + Filter Operator [FIL_22] (rows=8/8 width=4) + predicate:(b = 3) + TableScan [TS_1] (rows=40/40 width=4) + default@t8,tb,Tbl:COMPLETE,Col:COMPLETE,Output:["b"] + +PREHOOK: query: select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=8/8 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=8/8 width=8) + predicate:((b) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50) and (b = 2) and (2 = b)) + TableScan [TS_0] (rows=40/40 width=8) + default@t8,t8,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/1 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/1 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=8/8 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=8/8 width=8) + predicate:((b = 2) and ((b = 1) or (b = 2))) + TableScan [TS_0] (rows=40/40 width=8) + default@t8,t8,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/0 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/0 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/0 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=8/0 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=8/0 width=8) + predicate:((b = 2) and ((b = 1) or (b = 2)) and ((b = 1) or (b = 3))) + TableScan [TS_0] (rows=40/40 width=8) + default@t8,t8,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + +PREHOOK: query: select sum(a) from t8 where + b=2 and (b = 1 or b=2) +and + a=3 and (a = 3 or a=4) +group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t8 where + b=2 and (b = 1 or b=2) +and + a=3 and (a = 3 or a=4) +group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t8 where + b=2 and (b = 1 or b=2) +and + a=3 and (a = 3 or a=4) +group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t8 +#### A masked pattern was here #### +POSTHOOK: query: explain analyze select sum(a) from t8 where + b=2 and (b = 1 or b=2) +and + a=3 and (a = 3 or a=4) +group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t8 +#### A masked pattern was here #### +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 2 vectorized, llap + File Output Operator [FS_15] + Select Operator [SEL_14] (rows=1/0 width=8) + Output:["_col0"] + Group By Operator [GBY_13] (rows=1/0 width=12) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:2 + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_12] + PartitionCols:2 + Group By Operator [GBY_11] (rows=1/0 width=12) + Output:["_col0","_col1"],aggregations:["sum(a)"],keys:2 + Select Operator [SEL_10] (rows=2/0 width=8) + Output:["a"] + Filter Operator [FIL_9] (rows=2/0 width=8) + predicate:((b = 2) and ((b = 1) or (b = 2)) and (a = 3) and ((a = 3) or (a = 4))) + TableScan [TS_0] (rows=40/40 width=8) + default@t8,t8,Tbl:COMPLETE,Col:COMPLETE,Output:["a","b"] + diff --git ql/src/test/results/clientpositive/stats0.q.out ql/src/test/results/clientpositive/llap/stats0.q.out similarity index 63% rename from ql/src/test/results/clientpositive/stats0.q.out rename to ql/src/test/results/clientpositive/llap/stats0.q.out index 112247be7b..695ed643ab 100644 --- ql/src/test/results/clientpositive/stats0.q.out +++ ql/src/test/results/clientpositive/llap/stats0.q.out @@ -22,30 +22,111 @@ OPTIMIZED SQL: SELECT `key`, `value` FROM `default`.`src` STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.stats_non_partitioned + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct stats_non_partitioned { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.stats_non_partitioned + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### - table: + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -54,126 +135,59 @@ STAGE PLANS: bucketing_version 2 column.name.delimiter , columns key,value - columns.comments + columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_non_partitioned - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 + name: default.src + name: default.src + Truncated Path -> Alias: + /src [src] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [src] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -204,7 +218,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.stats_non_partitioned - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: #### A masked pattern was here #### @@ -766,64 +780,78 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@stats_partitioned@ds=1 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_partitioned - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) - outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 131500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - keys: ds (type: string) - minReductionHashAggr: 0.99 - mode: hash + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.stats_partitioned + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 500 Data size: 131500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct), _col2 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: struct), _col2 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -837,7 +865,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.stats_partitioned - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -1444,35 +1472,111 @@ OPTIMIZED SQL: SELECT `key`, `value` FROM `default`.`src` STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.stats_non_partitioned + numFiles 0 + numRows 0 + rawDataSize 0 + serialization.ddl struct stats_non_partitioned { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.stats_non_partitioned + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: src + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### - table: + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -1481,135 +1585,59 @@ STAGE PLANS: bucketing_version 2 column.name.delimiter , columns key,value - columns.comments + columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} + name default.src + numFiles 1 + numRows 500 + rawDataSize 5312 + serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_non_partitioned - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 + name: default.src + name: default.src + Truncated Path -> Alias: + /src [src] + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [src] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-7 - Conditional Operator + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1 + columns.types struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -1640,7 +1668,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.stats_non_partitioned - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: #### A masked pattern was here #### @@ -1650,194 +1678,6 @@ STAGE PLANS: Table: default.stats_non_partitioned Is Table Level Stats: true - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_non_partitioned - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_non_partitioned - name: default.stats_non_partitioned - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_non_partitioned - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string -#### A masked pattern was here #### - name default.stats_non_partitioned - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct stats_non_partitioned { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_non_partitioned - name: default.stats_non_partitioned - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - PREHOOK: query: insert overwrite table stats_non_partitioned select * from src PREHOOK: type: QUERY @@ -2390,78 +2230,78 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@stats_partitioned@ds=1 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_partitioned - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) - outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 131500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - keys: ds (type: string) - minReductionHashAggr: 0.99 - mode: hash + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.stats_partitioned + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 500 Data size: 131500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct), _col2 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: struct), _col2 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -2475,7 +2315,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.stats_partitioned - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -2483,36 +2323,6 @@ STAGE PLANS: Column Types: string, string Table: default.stats_partitioned - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_partitioned - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.stats_partitioned - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - PREHOOK: query: insert overwrite table stats_partitioned partition (ds='1') select * from src PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/stats1.q.out ql/src/test/results/clientpositive/llap/stats1.q.out similarity index 56% rename from ql/src/test/results/clientpositive/stats1.q.out rename to ql/src/test/results/clientpositive/llap/stats1.q.out index a2b269e260..e1c38ed13a 100644 --- ql/src/test/results/clientpositive/stats1.q.out +++ ql/src/test/results/clientpositive/llap/stats1.q.out @@ -34,116 +34,123 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Map 5 <- Union 3 (CONTAINS) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Union 3 (CONTAINS) + Reducer 4 <- Union 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: s2 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.96153843 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'tst1' (type: string), CAST( _col0 AS STRING) (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash + Select Operator + expressions: 'tst1' (type: string), CAST( _col0 AS STRING) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - TableScan - alias: s2 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable_n4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.96153843 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 26 Data size: 4647 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 26 Data size: 7072 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Union 3 + Vertex: Union 3 + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/stats10.q.out ql/src/test/results/clientpositive/llap/stats10.q.out similarity index 73% rename from ql/src/test/results/clientpositive/stats10.q.out rename to ql/src/test/results/clientpositive/llap/stats10.q.out index 8a38013477..5e0fb15365 100644 --- ql/src/test/results/clientpositive/stats10.q.out +++ ql/src/test/results/clientpositive/llap/stats10.q.out @@ -20,59 +20,93 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@bucket3_1_n0@ds=1 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(key) (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: int) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToInteger(key) (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket3_1_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) - outputColumnNames: key, value, ds - Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - keys: ds (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.bucket3_1_n0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 500 Data size: 90000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct), _col2 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -86,7 +120,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket3_1_n0 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -94,37 +128,6 @@ STAGE PLANS: Column Types: int, string Table: default.bucket3_1_n0 - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - PREHOOK: query: insert overwrite table bucket3_1_n0 partition (ds='1') select * from src PREHOOK: type: QUERY @@ -432,17 +435,21 @@ POSTHOOK: Output: default@bucket3_1_n0@ds=1 POSTHOOK: Output: default@bucket3_1_n0@ds=2 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: bucket3_1_n0 - Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: bucket3_1_n0 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: diff --git ql/src/test/results/clientpositive/stats12.q.out ql/src/test/results/clientpositive/llap/stats12.q.out similarity index 72% rename from ql/src/test/results/clientpositive/stats12.q.out rename to ql/src/test/results/clientpositive/llap/stats12.q.out index e84f6d4396..b82bb0bfcd 100644 --- ql/src/test/results/clientpositive/stats12.q.out +++ ql/src/test/results/clientpositive/llap/stats12.q.out @@ -53,117 +53,121 @@ POSTHOOK: Output: default@analyze_srcpart_n3@ds=2008-04-08/hr=11 POSTHOOK: Output: default@analyze_srcpart_n3@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart_n3 - Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE - Statistics Aggregation Key Prefix: default.analyze_srcpart_n3/ - GatherStats: true - Path -> Alias: + Tez #### A masked pattern was here #### - Path -> Partition: + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart_n3 + Statistics Aggregation Key Prefix: default.analyze_srcpart_n3/ + GatherStats: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: #### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string + Path -> Partition: #### A masked pattern was here #### - name default.analyze_srcpart_n3 - numFiles 1 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct analyze_srcpart_n3 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string + name default.analyze_srcpart_n3 + numFiles 1 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct analyze_srcpart_n3 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### - name default.analyze_srcpart_n3 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct analyze_srcpart_n3 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.analyze_srcpart_n3 - name: default.analyze_srcpart_n3 + name default.analyze_srcpart_n3 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct analyze_srcpart_n3 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.analyze_srcpart_n3 + name: default.analyze_srcpart_n3 #### A masked pattern was here #### - name default.analyze_srcpart_n3 - numFiles 1 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct analyze_srcpart_n3 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string + name default.analyze_srcpart_n3 + numFiles 1 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct analyze_srcpart_n3 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### - name default.analyze_srcpart_n3 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct analyze_srcpart_n3 { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.analyze_srcpart_n3 - name: default.analyze_srcpart_n3 - Truncated Path -> Alias: - /analyze_srcpart_n3/ds=2008-04-08/hr=11 [analyze_srcpart_n3] - /analyze_srcpart_n3/ds=2008-04-08/hr=12 [analyze_srcpart_n3] + name default.analyze_srcpart_n3 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct analyze_srcpart_n3 { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.analyze_srcpart_n3 + name: default.analyze_srcpart_n3 + Truncated Path -> Alias: + /analyze_srcpart_n3/ds=2008-04-08/hr=11 [analyze_srcpart_n3] + /analyze_srcpart_n3/ds=2008-04-08/hr=12 [analyze_srcpart_n3] - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: Stats Aggregation Key Prefix: default.analyze_srcpart_n3/ diff --git ql/src/test/results/clientpositive/stats13.q.out ql/src/test/results/clientpositive/llap/stats13.q.out similarity index 84% rename from ql/src/test/results/clientpositive/stats13.q.out rename to ql/src/test/results/clientpositive/llap/stats13.q.out index d271a42cba..6954cbd0b1 100644 --- ql/src/test/results/clientpositive/stats13.q.out +++ ql/src/test/results/clientpositive/llap/stats13.q.out @@ -49,70 +49,74 @@ POSTHOOK: Output: default@analyze_srcpart POSTHOOK: Output: default@analyze_srcpart@ds=2008-04-08/hr=11 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart - Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE - Statistics Aggregation Key Prefix: default.analyze_srcpart/ - GatherStats: true - Path -> Alias: + Tez #### A masked pattern was here #### - Path -> Partition: + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart + Statistics Aggregation Key Prefix: default.analyze_srcpart/ + GatherStats: true + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: #### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string + Path -> Partition: #### A masked pattern was here #### - name default.analyze_srcpart - numFiles 1 - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct analyze_srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string + name default.analyze_srcpart + numFiles 1 + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct analyze_srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 #### A masked pattern was here #### - name default.analyze_srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct analyze_srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments 'default','default' + columns.types string:string #### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.analyze_srcpart - name: default.analyze_srcpart - Truncated Path -> Alias: - /analyze_srcpart/ds=2008-04-08/hr=11 [analyze_srcpart] + name default.analyze_srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct analyze_srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.analyze_srcpart + name: default.analyze_srcpart + Truncated Path -> Alias: + /analyze_srcpart/ds=2008-04-08/hr=11 [analyze_srcpart] - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: Stats Aggregation Key Prefix: default.analyze_srcpart/ diff --git ql/src/test/results/clientpositive/stats2.q.out ql/src/test/results/clientpositive/llap/stats2.q.out similarity index 85% rename from ql/src/test/results/clientpositive/stats2.q.out rename to ql/src/test/results/clientpositive/llap/stats2.q.out index 409ba97305..06143a2b9a 100644 --- ql/src/test/results/clientpositive/stats2.q.out +++ ql/src/test/results/clientpositive/llap/stats2.q.out @@ -25,29 +25,37 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.analyze_t1 - Execution mode: vectorized + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.analyze_t1 + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -155,17 +163,21 @@ POSTHOOK: Output: default@analyze_t1@ds=2008-04-09/hr=11 POSTHOOK: Output: default@analyze_t1@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_t1 - Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_t1 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: diff --git ql/src/test/results/clientpositive/stats4.q.out ql/src/test/results/clientpositive/llap/stats4.q.out similarity index 88% rename from ql/src/test/results/clientpositive/stats4.q.out rename to ql/src/test/results/clientpositive/llap/stats4.q.out index 74f4c55428..2a6ca49af9 100644 --- ql/src/test/results/clientpositive/stats4.q.out +++ ql/src/test/results/clientpositive/llap/stats4.q.out @@ -56,116 +56,137 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0, Stage-10 - Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-9 depends on stages: Stage-1, Stage-10 - Stage-10 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ds <= '2008-04-08') (type: boolean) + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct), _col3 (type: struct) + Filter Operator + predicate: (ds > '2008-04-08') (type: boolean) + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.nzhang_part2 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, hr + Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: '2008-12-31' (type: string), hr (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: '2008-12-31' (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct), _col3 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part1 + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: key, value, ds, hr - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - keys: ds (type: string), hr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: struct), _col3 (type: struct) - Filter Operator - predicate: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part2 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: '2008-12-31' (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames: key, value, hr - Statistics: Num rows: 666 Data size: 303696 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - keys: '2008-12-31' (type: string), hr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: _col2 (type: struct), _col3 (type: struct), '2008-12-31' (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-8 - Conditional Operator - - Stage: Stage-5 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### + Stage: Stage-3 + Dependency Collection Stage: Stage-0 Move Operator @@ -180,7 +201,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part1 - Stage: Stage-3 + Stage: Stage-4 Stats Work Basic Stats Work: Column Stats Desc: @@ -188,36 +209,6 @@ STAGE PLANS: Column Types: string, string Table: default.nzhang_part1 - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part1 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.nzhang_part1 - - Stage: Stage-7 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - Stage: Stage-1 Move Operator tables: @@ -231,7 +222,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part2 - Stage: Stage-9 + Stage: Stage-5 Stats Work Basic Stats Work: Column Stats Desc: @@ -239,37 +230,6 @@ STAGE PLANS: Column Types: string, string Table: default.nzhang_part2 - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: '2008-12-31' (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: '2008-12-31' (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: struct), _col3 (type: struct), '2008-12-31' (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 2316 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - PREHOOK: query: from srcpart insert overwrite table nzhang_part1 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08' insert overwrite table nzhang_part2 partition(ds='2008-12-31', hr) select key, value, hr where ds > '2008-04-08' diff --git ql/src/test/results/clientpositive/stats5.q.out ql/src/test/results/clientpositive/llap/stats5.q.out similarity index 91% rename from ql/src/test/results/clientpositive/stats5.q.out rename to ql/src/test/results/clientpositive/llap/stats5.q.out index d9c8276d49..362f44e162 100644 --- ql/src/test/results/clientpositive/stats5.q.out +++ ql/src/test/results/clientpositive/llap/stats5.q.out @@ -20,17 +20,21 @@ POSTHOOK: Input: default@analyze_src POSTHOOK: Output: default@analyze_src STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_src + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: diff --git ql/src/test/results/clientpositive/stats7.q.out ql/src/test/results/clientpositive/llap/stats7.q.out similarity index 97% rename from ql/src/test/results/clientpositive/stats7.q.out rename to ql/src/test/results/clientpositive/llap/stats7.q.out index 5d85c0a712..7e64f7f155 100644 --- ql/src/test/results/clientpositive/stats7.q.out +++ ql/src/test/results/clientpositive/llap/stats7.q.out @@ -51,17 +51,21 @@ POSTHOOK: Output: default@analyze_srcpart_n4@ds=2008-04-08/hr=11 POSTHOOK: Output: default@analyze_srcpart_n4@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart_n4 - Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart_n4 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: diff --git ql/src/test/results/clientpositive/stats8.q.out ql/src/test/results/clientpositive/llap/stats8.q.out similarity index 95% rename from ql/src/test/results/clientpositive/stats8.q.out rename to ql/src/test/results/clientpositive/llap/stats8.q.out index 6a84cb8573..29b4dc1fa7 100644 --- ql/src/test/results/clientpositive/stats8.q.out +++ ql/src/test/results/clientpositive/llap/stats8.q.out @@ -82,17 +82,21 @@ POSTHOOK: Output: default@analyze_srcpart_n1 POSTHOOK: Output: default@analyze_srcpart_n1@ds=2008-04-08/hr=11 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart_n1 - Statistics: Num rows: 392 Data size: 235616 Basic stats: PARTIAL Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart_n1 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: @@ -235,17 +239,21 @@ POSTHOOK: Output: default@analyze_srcpart_n1 POSTHOOK: Output: default@analyze_srcpart_n1@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart_n1 - Statistics: Num rows: 794 Data size: 186024 Basic stats: PARTIAL Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart_n1 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: @@ -313,17 +321,21 @@ POSTHOOK: Output: default@analyze_srcpart_n1 POSTHOOK: Output: default@analyze_srcpart_n1@ds=2008-04-09/hr=11 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart_n1 - Statistics: Num rows: 1196 Data size: 136432 Basic stats: PARTIAL Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart_n1 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: @@ -391,17 +403,21 @@ POSTHOOK: Output: default@analyze_srcpart_n1 POSTHOOK: Output: default@analyze_srcpart_n1@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart_n1 - Statistics: Num rows: 1598 Data size: 86840 Basic stats: PARTIAL Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart_n1 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: @@ -481,17 +497,21 @@ POSTHOOK: Output: default@analyze_srcpart_n1@ds=2008-04-09/hr=11 POSTHOOK: Output: default@analyze_srcpart_n1@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcpart_n1 - Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcpart_n1 + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: diff --git ql/src/test/results/clientpositive/stats9.q.out ql/src/test/results/clientpositive/llap/stats9.q.out similarity index 91% rename from ql/src/test/results/clientpositive/stats9.q.out rename to ql/src/test/results/clientpositive/llap/stats9.q.out index 772df43201..dabeeaf03d 100644 --- ql/src/test/results/clientpositive/stats9.q.out +++ ql/src/test/results/clientpositive/llap/stats9.q.out @@ -26,17 +26,21 @@ POSTHOOK: Input: default@analyze_srcbucket POSTHOOK: Output: default@analyze_srcbucket STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: analyze_srcbucket - Statistics: Num rows: 391 Data size: 116030 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: analyze_srcbucket + Execution mode: llap + LLAP IO: no inputs - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: diff --git ql/src/test/results/clientpositive/llap/stats_empty_dyn_part.q.out ql/src/test/results/clientpositive/llap/stats_empty_dyn_part.q.out new file mode 100644 index 0000000000..d9bbe8a572 --- /dev/null +++ ql/src/test/results/clientpositive/llap/stats_empty_dyn_part.q.out @@ -0,0 +1,121 @@ +PREHOOK: query: create table tmptable_n7(key string) partitioned by (part string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmptable_n7 +POSTHOOK: query: create table tmptable_n7(key string) partitioned by (part string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmptable_n7 +PREHOOK: query: explain insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tmptable_n7 +POSTHOOK: query: explain insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (key = 'no_such_value') (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key = 'no_such_value') (type: boolean) + Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'no_such_value' (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable_n7 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, part + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll') + keys: part (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + part + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.tmptable_n7 + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key + Column Types: string + Table: default.tmptable_n7 + +PREHOOK: query: insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tmptable_n7 +POSTHOOK: query: insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src diff --git ql/src/test/results/clientpositive/stats_empty_partition.q.out ql/src/test/results/clientpositive/llap/stats_empty_partition.q.out similarity index 98% rename from ql/src/test/results/clientpositive/stats_empty_partition.q.out rename to ql/src/test/results/clientpositive/llap/stats_empty_partition.q.out index da759da2ae..fd81b1e57b 100644 --- ql/src/test/results/clientpositive/stats_empty_partition.q.out +++ ql/src/test/results/clientpositive/llap/stats_empty_partition.q.out @@ -37,7 +37,7 @@ Table: tmptable_n11 #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 1 + numFiles 0 numRows 0 rawDataSize 0 totalSize 0 diff --git ql/src/test/results/clientpositive/stats_empty_partition2.q.out ql/src/test/results/clientpositive/llap/stats_empty_partition2.q.out similarity index 62% rename from ql/src/test/results/clientpositive/stats_empty_partition2.q.out rename to ql/src/test/results/clientpositive/llap/stats_empty_partition2.q.out index 8241bfb604..27e8e4ac7b 100644 --- ql/src/test/results/clientpositive/stats_empty_partition2.q.out +++ ql/src/test/results/clientpositive/llap/stats_empty_partition2.q.out @@ -88,59 +88,73 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: p1_n0 - filterExpr: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator - predicate: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator - expressions: a (type: int), p (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: p1_n0 + filterExpr: a is not null (type: boolean) Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE - value expressions: _col1 (type: int) - TableScan - alias: t_n32 - filterExpr: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) + Filter Operator + predicate: a is not null (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Select Operator + expressions: a (type: int), p (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: COMPLETE + value expressions: _col1 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: t_n32 + filterExpr: a is not null (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Filter Operator + predicate: a is not null (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: a (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/stats_nonpart.q.out ql/src/test/results/clientpositive/llap/stats_nonpart.q.out similarity index 77% rename from ql/src/test/results/clientpositive/stats_nonpart.q.out rename to ql/src/test/results/clientpositive/llap/stats_nonpart.q.out index 0de4916913..29eab6390d 100644 --- ql/src/test/results/clientpositive/stats_nonpart.q.out +++ ql/src/test/results/clientpositive/llap/stats_nonpart.q.out @@ -116,61 +116,75 @@ POSTHOOK: Input: default@mysource POSTHOOK: Output: default@stats_nonpartitioned STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mysource - filterExpr: (p = 100) (type: boolean) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 100 (type: int), key (type: int) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: mysource + filterExpr: (p = 100) (type: boolean) + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (p = 100) (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 100 (type: int), key (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.stats_nonpartitioned + Write Type: INSERT + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat - serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde - name: default.stats_nonpartitioned - Write Type: INSERT - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: key, value - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -183,7 +197,7 @@ STAGE PLANS: name: default.stats_nonpartitioned Write Type: INSERT - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: diff --git ql/src/test/results/clientpositive/stats_part.q.out ql/src/test/results/clientpositive/llap/stats_part.q.out similarity index 91% rename from ql/src/test/results/clientpositive/stats_part.q.out rename to ql/src/test/results/clientpositive/llap/stats_part.q.out index 82259f6a06..1c1d248dfa 100644 --- ql/src/test/results/clientpositive/stats_part.q.out +++ ql/src/test/results/clientpositive/llap/stats_part.q.out @@ -76,44 +76,53 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: stats_part - filterExpr: (p > 100) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p > 100) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: key - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: stats_part + filterExpr: (p > 100) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (p > 100) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(key) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: unknown + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -220,7 +229,7 @@ Table Parameters: numPartitions 3 numRows 6 rawDataSize 0 - totalSize 2250 + totalSize 2274 transactional true transactional_properties default #### A masked pattern was here #### @@ -283,7 +292,7 @@ Table Parameters: numPartitions 3 numRows 8 rawDataSize 0 - totalSize 3006 + totalSize 3042 transactional true transactional_properties default #### A masked pattern was here #### @@ -442,7 +451,7 @@ Table Parameters: numPartitions 3 numRows 8 rawDataSize 0 - totalSize 3006 + totalSize 3042 transactional true transactional_properties default #### A masked pattern was here #### @@ -529,7 +538,7 @@ Table Parameters: numPartitions 3 numRows 8 rawDataSize 0 - totalSize 3006 + totalSize 3042 transactional true transactional_properties default #### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/stats_part2.q.out ql/src/test/results/clientpositive/llap/stats_part2.q.out similarity index 81% rename from ql/src/test/results/clientpositive/stats_part2.q.out rename to ql/src/test/results/clientpositive/llap/stats_part2.q.out index ceb3f51d32..0fbd42db6e 100644 --- ql/src/test/results/clientpositive/stats_part2.q.out +++ ql/src/test/results/clientpositive/llap/stats_part2.q.out @@ -58,42 +58,51 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: stats_part - filterExpr: (p > 100) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p > 100) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: stats_part + filterExpr: (p > 100) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (p > 100) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: unknown + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -115,44 +124,53 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: stats_part - filterExpr: (p > 100) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p > 100) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: key - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(key) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: stats_part + filterExpr: (p > 100) (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + Filter Operator + predicate: (p > 100) (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(key) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: unknown + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -255,11 +273,11 @@ Table Type: MANAGED_TABLE Table Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} bucketing_version 2 - numFiles 3 + numFiles 6 numPartitions 3 numRows 6 rawDataSize 0 - totalSize 2341 + totalSize 4387 transactional true transactional_properties default #### A masked pattern was here #### @@ -354,11 +372,11 @@ Table Type: MANAGED_TABLE Table Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} bucketing_version 2 - numFiles 4 + numFiles 8 numPartitions 3 numRows 8 rawDataSize 0 - totalSize 3132 + totalSize 5850 transactional true transactional_properties default #### A masked pattern was here #### @@ -511,10 +529,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 1 + numFiles 2 numRows 2 rawDataSize 0 - totalSize 758 + totalSize 1459 #### A masked pattern was here #### # Storage Information @@ -548,10 +566,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 1 + numFiles 2 numRows 2 rawDataSize 0 - totalSize 791 + totalSize 1464 #### A masked pattern was here #### # Storage Information @@ -585,10 +603,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 2 + numFiles 4 numRows 4 rawDataSize 0 - totalSize 1583 + totalSize 2927 #### A masked pattern was here #### # Storage Information @@ -633,41 +651,50 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: stats_part - filterExpr: (p > 100) (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: stats_part + filterExpr: (p > 100) (type: boolean) + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(key) + minReductionHashAggr: 0.8333333 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: may be used (ACID table) + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: max(key) - minReductionHashAggr: 0.99 - mode: hash + aggregations: max(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -709,10 +736,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 1 + numFiles 2 numRows 2 rawDataSize 0 - totalSize 758 + totalSize 1459 #### A masked pattern was here #### # Storage Information @@ -746,10 +773,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 3 + numFiles 4 numRows 2 rawDataSize 0 - totalSize 2240 + totalSize 2913 #### A masked pattern was here #### # Storage Information @@ -783,10 +810,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 2 + numFiles 4 numRows 4 rawDataSize 0 - totalSize 1583 + totalSize 2927 #### A masked pattern was here #### # Storage Information @@ -849,10 +876,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 1 + numFiles 2 numRows 2 rawDataSize 0 - totalSize 758 + totalSize 1459 #### A masked pattern was here #### # Storage Information @@ -886,10 +913,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 3 + numFiles 4 numRows 2 rawDataSize 0 - totalSize 2240 + totalSize 2913 #### A masked pattern was here #### # Storage Information @@ -923,10 +950,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 2 + numFiles 4 numRows 4 rawDataSize 0 - totalSize 1583 + totalSize 2927 #### A masked pattern was here #### # Storage Information @@ -993,10 +1020,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 2 + numFiles 3 numRows 1 rawDataSize 0 - totalSize 1455 + totalSize 2163 #### A masked pattern was here #### # Storage Information @@ -1030,10 +1057,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 4 + numFiles 5 numRows 1 rawDataSize 0 - totalSize 2935 + totalSize 3611 #### A masked pattern was here #### # Storage Information @@ -1067,10 +1094,10 @@ Table: stats_part #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}} - numFiles 2 + numFiles 4 numRows 4 rawDataSize 0 - totalSize 1583 + totalSize 2927 #### A masked pattern was here #### # Storage Information @@ -1157,40 +1184,49 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: stats_part - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: key - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: stats_part + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(key) + minReductionHashAggr: 0.8333333 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: may be used (ACID table) + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count(key) - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1258,41 +1294,50 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: stats_part - filterExpr: (p > 100) (type: boolean) - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: key - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: stats_part + filterExpr: (p > 100) (type: boolean) + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(key) + minReductionHashAggr: 0.8 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: may be used (ACID table) + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: max(key) - minReductionHashAggr: 0.99 - mode: hash + aggregations: max(VALUE._col0) + mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + File Output Operator + compressed: false Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/stats_partial_size.q.out ql/src/test/results/clientpositive/llap/stats_partial_size.q.out new file mode 100644 index 0000000000..c2b836ac70 --- /dev/null +++ ql/src/test/results/clientpositive/llap/stats_partial_size.q.out @@ -0,0 +1,144 @@ +PREHOOK: query: create table sample_partitioned (x int) partitioned by (y int) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@sample_partitioned +POSTHOOK: query: create table sample_partitioned (x int) partitioned by (y int) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@sample_partitioned +PREHOOK: query: insert into sample_partitioned partition(y=1) values (1),(2) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@sample_partitioned@y=1 +POSTHOOK: query: insert into sample_partitioned partition(y=1) values (1),(2) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@sample_partitioned@y=1 +POSTHOOK: Lineage: sample_partitioned PARTITION(y=1).x SCRIPT [] +PREHOOK: query: create temporary table sample as select * from sample_partitioned +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@sample_partitioned +PREHOOK: Input: default@sample_partitioned@y=1 +PREHOOK: Output: database:default +PREHOOK: Output: default@sample +POSTHOOK: query: create temporary table sample as select * from sample_partitioned +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@sample_partitioned +POSTHOOK: Input: default@sample_partitioned@y=1 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@sample +PREHOOK: query: analyze table sample compute statistics for columns +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@sample +PREHOOK: Output: default@sample +#### A masked pattern was here #### +POSTHOOK: query: analyze table sample compute statistics for columns +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@sample +POSTHOOK: Output: default@sample +#### A masked pattern was here #### +PREHOOK: query: explain select sample_partitioned.x from sample_partitioned, sample where sample.y = sample_partitioned.y +PREHOOK: type: QUERY +PREHOOK: Input: default@sample +PREHOOK: Input: default@sample_partitioned +PREHOOK: Input: default@sample_partitioned@y=1 +#### A masked pattern was here #### +POSTHOOK: query: explain select sample_partitioned.x from sample_partitioned, sample where sample.y = sample_partitioned.y +POSTHOOK: type: QUERY +POSTHOOK: Input: default@sample +POSTHOOK: Input: default@sample_partitioned +POSTHOOK: Input: default@sample_partitioned@y=1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: sample_partitioned + filterExpr: y is not null (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: x (type: int), y (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: sample + filterExpr: y is not null (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: y is not null (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: y (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: int) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Dynamic Partitioning Event Operator + Target column: y (int) + Target Input: sample_partitioned + Partition key expr: y + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Target Vertex: Map 1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/stats_ppr_all.q.out ql/src/test/results/clientpositive/llap/stats_ppr_all.q.out new file mode 100644 index 0000000000..5cefd2cf76 --- /dev/null +++ ql/src/test/results/clientpositive/llap/stats_ppr_all.q.out @@ -0,0 +1,374 @@ +PREHOOK: query: drop table ss +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table ss +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE ss ( + sales_order_id BIGINT, + order_amount FLOAT) +PARTITIONED BY (country STRING, year INT, month INT, day INT) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ss +POSTHOOK: query: CREATE TABLE ss ( + sales_order_id BIGINT, + order_amount FLOAT) +PARTITIONED BY (country STRING, year INT, month INT, day INT) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ss +PREHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=1) values(1,22.0) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 +POSTHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=1) values(1,22.0) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 +POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=1).order_amount SCRIPT [] +POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=1).sales_order_id SCRIPT [] +PREHOOK: query: insert into ss partition(country="US", year=2015, month=2, day=1) values(2,2.0) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 +POSTHOOK: query: insert into ss partition(country="US", year=2015, month=2, day=1) values(2,2.0) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 +POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=2,day=1).order_amount SCRIPT [] +POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=2,day=1).sales_order_id SCRIPT [] +PREHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=2) values(1,2.0) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 +POSTHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=2) values(1,2.0) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 +POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=2).order_amount SCRIPT [] +POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=2).sales_order_id SCRIPT [] +PREHOOK: query: ANALYZE TABLE ss PARTITION(country,year,month,day) compute statistics for columns +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@ss +PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 +PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 +PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +PREHOOK: Output: default@ss +PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 +PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 +PREHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +POSTHOOK: query: ANALYZE TABLE ss PARTITION(country,year,month,day) compute statistics for columns +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@ss +POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 +POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 +POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +POSTHOOK: Output: default@ss +POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 +POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 +POSTHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +PREHOOK: query: explain select sum(order_amount) from ss where (country="US" and year=2015 and month=2 and day=1) +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(order_amount) from ss where (country="US" and year=2015 and month=2 and day=1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + filterExpr: ((country = 'US') and (year = 2015) and (month = 2) and (day = 1)) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: order_amount (type: float) + outputColumnNames: order_amount + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(order_amount) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select sum(order_amount) from ss where (year*10000+month*100+day) = "2015010" and 1>0 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(order_amount) from ss where (year*10000+month*100+day) = "2015010" and 1>0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + filterExpr: (UDFToDouble((((year * 10000) + (month * 100)) + day)) = 2015010.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble((((year * 10000) + (month * 100)) + day)) = 2015010.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: order_amount (type: float) + outputColumnNames: order_amount + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(order_amount) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) + Execution mode: vectorized, llap + LLAP IO: unknown + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) = "201511" and 1>0 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) = "201511" and 1>0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + filterExpr: (201511.0D = 201511.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: order_amount (type: float) + outputColumnNames: order_amount + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(order_amount) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) > "201511" and 1>0 +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 +PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +POSTHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) > "201511" and 1>0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 +POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: ss + filterExpr: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) + Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: order_amount (type: float) + outputColumnNames: order_amount + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(order_amount) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: double) + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select '1' from ss where (year*100+month*10+day) > "201511" +PREHOOK: type: QUERY +PREHOOK: Input: default@ss +PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 +PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +POSTHOOK: query: explain select '1' from ss where (year*100+month*10+day) > "201511" +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ss +POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 +POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: ss + filterExpr: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) + Filter Operator + predicate: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) + Select Operator + expressions: '1' (type: string) + outputColumnNames: _col0 + ListSink + diff --git ql/src/test/results/clientpositive/stats_sizebug.q.out ql/src/test/results/clientpositive/llap/stats_sizebug.q.out similarity index 68% rename from ql/src/test/results/clientpositive/stats_sizebug.q.out rename to ql/src/test/results/clientpositive/llap/stats_sizebug.q.out index 984aaf53c6..4c78c23c4b 100644 --- ql/src/test/results/clientpositive/stats_sizebug.q.out +++ ql/src/test/results/clientpositive/llap/stats_sizebug.q.out @@ -52,61 +52,75 @@ POSTHOOK: Input: default@mysource POSTHOOK: Output: default@stats_nonpartitioned STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mysource - filterExpr: (p = 100) (type: boolean) - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (p = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 100 (type: int), key (type: int) + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: mysource + filterExpr: (p = 100) (type: boolean) + Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (p = 100) (type: boolean) + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 100 (type: int), key (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.stats_nonpartitioned + Write Type: INSERT + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: key, value + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE table: - input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat - serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde - name: default.stats_nonpartitioned - Write Type: INSERT - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: key, value - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -119,7 +133,7 @@ STAGE PLANS: name: default.stats_nonpartitioned Write Type: INSERT - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: diff --git ql/src/test/results/clientpositive/structin.q.out ql/src/test/results/clientpositive/llap/structin.q.out similarity index 57% rename from ql/src/test/results/clientpositive/structin.q.out rename to ql/src/test/results/clientpositive/llap/structin.q.out index 18999c5cd9..2cc570b746 100644 --- ql/src/test/results/clientpositive/structin.q.out +++ ql/src/test/results/clientpositive/llap/structin.q.out @@ -37,38 +37,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@t11_n1 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t11_n1 - filterExpr: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1'), const struct('1234-1111-0074580704','1'), const struct('1234-1111-0074581619','2'), const struct('1234-1111-0074582745','1'), const struct('1234-1111-0074586625','1'), const struct('1234-1111-0074019112','1'), const struct('1234-1111-0074019610','1'), const struct('1234-1111-0074022106','1')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1'), const struct('1234-1111-0074580704','1'), const struct('1234-1111-0074581619','2'), const struct('1234-1111-0074582745','1'), const struct('1234-1111-0074586625','1'), const struct('1234-1111-0074019112','1'), const struct('1234-1111-0074019610','1'), const struct('1234-1111-0074022106','1')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: id (type: string), lineid (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: t11_n1 + filterExpr: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1'), const struct('1234-1111-0074580704','1'), const struct('1234-1111-0074581619','2'), const struct('1234-1111-0074582745','1'), const struct('1234-1111-0074586625','1'), const struct('1234-1111-0074019112','1'), const struct('1234-1111-0074019610','1'), const struct('1234-1111-0074022106','1')) (type: boolean) + Filter Operator + predicate: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1'), const struct('1234-1111-0074580704','1'), const struct('1234-1111-0074581619','2'), const struct('1234-1111-0074582745','1'), const struct('1234-1111-0074586625','1'), const struct('1234-1111-0074019112','1'), const struct('1234-1111-0074019610','1'), const struct('1234-1111-0074022106','1')) (type: boolean) + Select Operator + expressions: id (type: string), lineid (type: string) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: explain select * from t11_n1 where struct(`id`, `lineid`) IN ( @@ -87,38 +71,22 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@t11_n1 #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 + Stage-0 is a root stage STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t11_n1 - filterExpr: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: id (type: string), lineid (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - ListSink + TableScan + alias: t11_n1 + filterExpr: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1')) (type: boolean) + Filter Operator + predicate: (struct(id,lineid)) IN (const struct('1234-1111-0074578664','3'), const struct('1234-1111-0074578695','1')) (type: boolean) + Select Operator + expressions: id (type: string), lineid (type: string) + outputColumnNames: _col0, _col1 + ListSink PREHOOK: query: CREATE TABLE test_struct ( @@ -187,38 +155,47 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: test_struct - filterExpr: ((datestr = '02-02-2020') and demo_struct is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((datestr = '02-02-2020') and demo_struct is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test_struct + filterExpr: ((datestr = '02-02-2020') and demo_struct is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((datestr = '02-02-2020') and demo_struct is not null) (type: boolean) + Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: f1 (type: string), demo_struct (type: struct) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Select Operator - expressions: f1 (type: string), demo_struct (type: struct) - outputColumnNames: _col0, _col1 + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: struct), '02-02-2020' (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + + File Output Operator + compressed: false Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: struct), '02-02-2020' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 2658 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/subq.q.out ql/src/test/results/clientpositive/llap/subq.q.out new file mode 100644 index 0000000000..b68571b6e9 --- /dev/null +++ ql/src/test/results/clientpositive/llap/subq.q.out @@ -0,0 +1,156 @@ +PREHOOK: query: EXPLAIN +FROM ( + FROM src select src.* WHERE src.key < 100 +) unioninput +INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: target/warehouse/union.out +POSTHOOK: query: EXPLAIN +FROM ( + FROM src select src.* WHERE src.key < 100 +) unioninput +INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: target/warehouse/union.out +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + files: + hdfs directory: true + destination: target/warehouse/union.out + +PREHOOK: query: FROM ( + FROM src select src.* WHERE src.key < 100 +) unioninput +INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: target/warehouse/union.out +POSTHOOK: query: FROM ( + FROM src select src.* WHERE src.key < 100 +) unioninput +INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: target/warehouse/union.out +86val_86 +27val_27 +98val_98 +66val_66 +37val_37 +15val_15 +82val_82 +17val_17 +0val_0 +57val_57 +20val_20 +92val_92 +47val_47 +72val_72 +4val_4 +35val_35 +54val_54 +51val_51 +65val_65 +83val_83 +12val_12 +67val_67 +84val_84 +58val_58 +8val_8 +24val_24 +42val_42 +0val_0 +96val_96 +26val_26 +51val_51 +43val_43 +95val_95 +98val_98 +85val_85 +77val_77 +0val_0 +87val_87 +15val_15 +72val_72 +90val_90 +19val_19 +10val_10 +5val_5 +58val_58 +35val_35 +95val_95 +11val_11 +34val_34 +42val_42 +78val_78 +76val_76 +41val_41 +30val_30 +64val_64 +76val_76 +74val_74 +69val_69 +33val_33 +70val_70 +5val_5 +2val_2 +35val_35 +80val_80 +44val_44 +53val_53 +90val_90 +12val_12 +5val_5 +70val_70 +24val_24 +70val_70 +83val_83 +26val_26 +67val_67 +18val_18 +9val_9 +18val_18 +97val_97 +84val_84 +28val_28 +37val_37 +90val_90 +97val_97 diff --git ql/src/test/results/clientpositive/subq2.q.out ql/src/test/results/clientpositive/llap/subq2.q.out similarity index 57% rename from ql/src/test/results/clientpositive/subq2.q.out rename to ql/src/test/results/clientpositive/llap/subq2.q.out index 007f2f44e7..edf93e17ee 100644 --- ql/src/test/results/clientpositive/subq2.q.out +++ ql/src/test/results/clientpositive/llap/subq2.q.out @@ -18,44 +18,53 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: (UDFToDouble(key) >= 90.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) >= 90.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + filterExpr: (UDFToDouble(key) >= 90.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) >= 90.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) + File Output Operator + compressed: false Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/subq_where_serialization.q.out ql/src/test/results/clientpositive/llap/subq_where_serialization.q.out new file mode 100644 index 0000000000..bb3084386c --- /dev/null +++ ql/src/test/results/clientpositive/llap/subq_where_serialization.q.out @@ -0,0 +1,86 @@ +PREHOOK: query: explain select src.key from src where src.key in ( select distinct key from src) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select src.key from src where src.key in ( select distinct key from src) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 2 + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: src + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/subquery_alias.q.out ql/src/test/results/clientpositive/llap/subquery_alias.q.out similarity index 74% rename from ql/src/test/results/clientpositive/subquery_alias.q.out rename to ql/src/test/results/clientpositive/llap/subquery_alias.q.out index 02e9ce494f..c4411ab58b 100644 --- ql/src/test/results/clientpositive/subquery_alias.q.out +++ ql/src/test/results/clientpositive/llap/subquery_alias.q.out @@ -16,79 +16,45 @@ POSTHOOK: Input: default@src POSTHOOK: Output: target/warehouse/union.out STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-6 depends on stages: Stage-1 , consists of Stage-3, Stage-2, Stage-4 - Stage-3 - Stage-0 depends on stages: Stage-3, Stage-2, Stage-5 - Stage-2 - Stage-4 - Stage-5 depends on stages: Stage-4 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-6 - Conditional Operator - - Stage: Stage-3 - Move Operator - files: - hdfs directory: true + Tez #### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - files: - hdfs directory: true - destination: target/warehouse/union.out + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (UDFToDouble(key) < 100.0D) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized, llap + LLAP IO: no inputs Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Dependency Collection - Stage: Stage-5 + Stage: Stage-0 Move Operator files: hdfs directory: true -#### A masked pattern was here #### + destination: target/warehouse/union.out PREHOOK: query: EXPLAIN SELECT * FROM @@ -116,11 +82,9 @@ STAGE PLANS: Processor Tree: TableScan alias: s - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE ListSink PREHOOK: query: SELECT * FROM diff --git ql/src/test/results/clientpositive/llap/subquery_exists_having.q.out ql/src/test/results/clientpositive/llap/subquery_exists_having.q.out new file mode 100644 index 0000000000..dc6b1af1d4 --- /dev/null +++ ql/src/test/results/clientpositive/llap/subquery_exists_having.q.out @@ -0,0 +1,418 @@ +PREHOOK: query: explain +select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((value > 'val_9') and key is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_9') and key is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +90 3 +92 1 +95 2 +96 1 +97 2 +98 2 +PREHOOK: query: explain +select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((value > 'val_9') and key is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_9') and key is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select b.key, count(*) +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +90 3 +92 1 +95 2 +96 1 +97 2 +98 2 +PREHOOK: query: create view cv1_n6 as +select b.key, count(*) as c +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +PREHOOK: type: CREATEVIEW +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@cv1_n6 +POSTHOOK: query: create view cv1_n6 as +select b.key, count(*) as c +from src b +group by b.key +having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +POSTHOOK: type: CREATEVIEW +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@cv1_n6 +POSTHOOK: Lineage: cv1_n6.c EXPRESSION [(src)b.null, ] +POSTHOOK: Lineage: cv1_n6.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] +PREHOOK: query: select * from cv1_n6 +PREHOOK: type: QUERY +PREHOOK: Input: default@cv1_n6 +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * from cv1_n6 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@cv1_n6 +POSTHOOK: Input: default@src +#### A masked pattern was here #### +90 3 +92 1 +95 2 +96 1 +97 2 +98 2 +PREHOOK: query: select * +from (select b.key, count(*) + from src b + group by b.key + having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +) a +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * +from (select b.key, count(*) + from src b + group by b.key + having exists + (select a.key + from src a + where a.key = b.key and a.value > 'val_9' + ) +) a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +90 3 +92 1 +95 2 +96 1 +97 2 +98 2 +PREHOOK: query: select b.key, min(b.value) +from src b +group by b.key +having exists ( select a.key + from src a + where a.value > 'val_9' and a.value = min(b.value) + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select b.key, min(b.value) +from src b +group by b.key +having exists ( select a.key + from src a + where a.value > 'val_9' and a.value = min(b.value) + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +90 val_90 +92 val_92 +95 val_95 +96 val_96 +97 val_97 +98 val_98 diff --git ql/src/test/results/clientpositive/llap/subquery_multiinsert.q.out ql/src/test/results/clientpositive/llap/subquery_multiinsert.q.out new file mode 100644 index 0000000000..5c5e5c3da9 --- /dev/null +++ ql/src/test/results/clientpositive/llap/subquery_multiinsert.q.out @@ -0,0 +1,1037 @@ +PREHOOK: query: CREATE TABLE src_4( + key STRING, + value STRING +) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src_4 +POSTHOOK: query: CREATE TABLE src_4( + key STRING, + value STRING +) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_4 +RUN: Stage-0:DDL +PREHOOK: query: CREATE TABLE src_5( + key STRING, + value STRING +) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src_5 +POSTHOOK: query: CREATE TABLE src_5( + key STRING, + value STRING +) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_5 +RUN: Stage-0:DDL +Warning: Shuffle Join MERGEJOIN[78][tables = [b, sq_2_notin_nullcheck]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain +from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_4 +PREHOOK: Output: default@src_5 +POSTHOOK: query: explain +from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_4 +POSTHOOK: Output: default@src_5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Reducer 9 (XPROD_EDGE) + Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 5 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) + Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE) + Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: key (type: string), value (type: string) + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string), value (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 7 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 8 + Map Operator Tree: + TableScan + alias: s1 + filterExpr: ((key > '2') or ((key > '2') and key is null)) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '2') and key is null) (type: boolean) + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 762 Data size: 158517 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col5 is null (type: boolean) + Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 key (type: string), value (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 = 0L) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: 0L (type: bigint) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_5 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_5 + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_4 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_4 + +Warning: Shuffle Join MERGEJOIN[78][tables = [b, sq_2_notin_nullcheck]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_4 +PREHOOK: Output: default@src_5 +POSTHOOK: query: from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_4 +POSTHOOK: Output: default@src_5 +POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] +RUN: Stage-2:MAPRED +RUN: Stage-3:DEPENDENCY_COLLECTION +RUN: Stage-1:MOVE +RUN: Stage-0:MOVE +RUN: Stage-4:STATS +RUN: Stage-5:STATS +PREHOOK: query: select * from src_4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_4 +#### A masked pattern was here #### +90 val_90 +90 val_90 +90 val_90 +92 val_92 +95 val_95 +95 val_95 +96 val_96 +97 val_97 +97 val_97 +98 val_98 +98 val_98 +PREHOOK: query: select * from src_5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_5 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +10 val_10 +100 val_100 +100 val_100 +103 val_103 +103 val_103 +104 val_104 +104 val_104 +105 val_105 +11 val_11 +111 val_111 +113 val_113 +113 val_113 +114 val_114 +116 val_116 +118 val_118 +118 val_118 +119 val_119 +119 val_119 +119 val_119 +12 val_12 +12 val_12 +120 val_120 +120 val_120 +125 val_125 +125 val_125 +126 val_126 +128 val_128 +128 val_128 +128 val_128 +129 val_129 +129 val_129 +131 val_131 +133 val_133 +134 val_134 +134 val_134 +136 val_136 +137 val_137 +137 val_137 +138 val_138 +138 val_138 +138 val_138 +138 val_138 +143 val_143 +145 val_145 +146 val_146 +146 val_146 +149 val_149 +149 val_149 +15 val_15 +15 val_15 +150 val_150 +152 val_152 +152 val_152 +153 val_153 +155 val_155 +156 val_156 +157 val_157 +158 val_158 +160 val_160 +162 val_162 +163 val_163 +164 val_164 +164 val_164 +165 val_165 +165 val_165 +166 val_166 +167 val_167 +167 val_167 +167 val_167 +168 val_168 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +17 val_17 +170 val_170 +172 val_172 +172 val_172 +174 val_174 +174 val_174 +175 val_175 +175 val_175 +176 val_176 +176 val_176 +177 val_177 +178 val_178 +179 val_179 +179 val_179 +18 val_18 +18 val_18 +180 val_180 +181 val_181 +183 val_183 +186 val_186 +187 val_187 +187 val_187 +187 val_187 +189 val_189 +19 val_19 +190 val_190 +191 val_191 +191 val_191 +192 val_192 +193 val_193 +193 val_193 +193 val_193 +194 val_194 +195 val_195 +195 val_195 +196 val_196 +197 val_197 +197 val_197 +199 val_199 +199 val_199 +199 val_199 +2 val_2 +Warning: Map Join MAPJOIN[78][bigTable=b] in task 'Map 1' is a cross product +PREHOOK: query: explain +from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_4 +PREHOOK: Output: default@src_5 +POSTHOOK: query: explain +from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_4 +POSTHOOK: Output: default@src_5 +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 4 (BROADCAST_EDGE), Map 5 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 key (type: string), value (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + input vertices: + 1 Map 4 + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_4 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Map Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + input vertices: + 1 Reducer 6 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col5 + input vertices: + 1 Map 5 + Statistics: Num rows: 762 Data size: 158517 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col5 is null (type: boolean) + Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: s1 + filterExpr: ((key > '2') or ((key > '2') and key is null)) (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '2') (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '2') and key is null) (type: boolean) + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_5 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: complete + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 = 0L) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: 0L (type: bigint) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + + Stage: Stage-3 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_4 + + Stage: Stage-4 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_4 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.src_5 + + Stage: Stage-5 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_5 + +Warning: Map Join MAPJOIN[78][bigTable=b] in task 'Map 1' is a cross product +PREHOOK: query: from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@src_4 +PREHOOK: Output: default@src_5 +POSTHOOK: query: from src b +INSERT OVERWRITE TABLE src_4 + select * + where b.key in + (select a.key + from src a + where b.value = a.value and a.key > '9' + ) +INSERT OVERWRITE TABLE src_5 + select * + where b.key not in ( select key from src s1 where s1.key > '2') + order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@src_4 +POSTHOOK: Output: default@src_5 +POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] +RUN: Stage-2:MAPRED +RUN: Stage-3:DEPENDENCY_COLLECTION +RUN: Stage-0:MOVE +RUN: Stage-1:MOVE +RUN: Stage-4:STATS +RUN: Stage-5:STATS +PREHOOK: query: select * from src_4 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_4 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_4 +#### A masked pattern was here #### +90 val_90 +90 val_90 +90 val_90 +92 val_92 +95 val_95 +95 val_95 +96 val_96 +97 val_97 +97 val_97 +98 val_98 +98 val_98 +PREHOOK: query: select * from src_5 +PREHOOK: type: QUERY +PREHOOK: Input: default@src_5 +#### A masked pattern was here #### +POSTHOOK: query: select * from src_5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_5 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +10 val_10 +100 val_100 +100 val_100 +103 val_103 +103 val_103 +104 val_104 +104 val_104 +105 val_105 +11 val_11 +111 val_111 +113 val_113 +113 val_113 +114 val_114 +116 val_116 +118 val_118 +118 val_118 +119 val_119 +119 val_119 +119 val_119 +12 val_12 +12 val_12 +120 val_120 +120 val_120 +125 val_125 +125 val_125 +126 val_126 +128 val_128 +128 val_128 +128 val_128 +129 val_129 +129 val_129 +131 val_131 +133 val_133 +134 val_134 +134 val_134 +136 val_136 +137 val_137 +137 val_137 +138 val_138 +138 val_138 +138 val_138 +138 val_138 +143 val_143 +145 val_145 +146 val_146 +146 val_146 +149 val_149 +149 val_149 +15 val_15 +15 val_15 +150 val_150 +152 val_152 +152 val_152 +153 val_153 +155 val_155 +156 val_156 +157 val_157 +158 val_158 +160 val_160 +162 val_162 +163 val_163 +164 val_164 +164 val_164 +165 val_165 +165 val_165 +166 val_166 +167 val_167 +167 val_167 +167 val_167 +168 val_168 +169 val_169 +169 val_169 +169 val_169 +169 val_169 +17 val_17 +170 val_170 +172 val_172 +172 val_172 +174 val_174 +174 val_174 +175 val_175 +175 val_175 +176 val_176 +176 val_176 +177 val_177 +178 val_178 +179 val_179 +179 val_179 +18 val_18 +18 val_18 +180 val_180 +181 val_181 +183 val_183 +186 val_186 +187 val_187 +187 val_187 +187 val_187 +189 val_189 +19 val_19 +190 val_190 +191 val_191 +191 val_191 +192 val_192 +193 val_193 +193 val_193 +193 val_193 +194 val_194 +195 val_195 +195 val_195 +196 val_196 +197 val_197 +197 val_197 +199 val_199 +199 val_199 +199 val_199 +2 val_2 diff --git ql/src/test/results/clientpositive/subquery_notexists.q.out ql/src/test/results/clientpositive/llap/subquery_notexists.q.out similarity index 60% rename from ql/src/test/results/clientpositive/subquery_notexists.q.out rename to ql/src/test/results/clientpositive/llap/subquery_notexists.q.out index b2b93b3814..c620c47c22 100644 --- ql/src/test/results/clientpositive/subquery_notexists.q.out +++ ql/src/test/results/clientpositive/llap/subquery_notexists.q.out @@ -21,98 +21,94 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_2') and key is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 631 Data size: 112846 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 is null (type: boolean) + Statistics: Num rows: 500 Data size: 89420 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: true (type: boolean), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 631 Data size: 112846 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 500 Data size: 89420 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: true (type: boolean), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string), _col2 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: boolean) Stage: Stage-0 Fetch Operator @@ -282,108 +278,104 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: (value > 'val_2') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (value > 'val_2') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Filter Operator + predicate: (value > 'val_2') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: value (type: string), key (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 566 Data size: 101016 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 is null (type: boolean) + Statistics: Num rows: 500 Data size: 89236 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - keys: value (type: string), key (type: string) - minReductionHashAggr: 0.99 - mode: hash + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col1 Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col1 (type: string) - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 635 Data size: 113574 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 500 Data size: 89428 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Group By Operator + keys: _col1 (type: string) + mode: complete + outputColumnNames: _col0 + Statistics: Num rows: 41 Data size: 3731 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: true (type: boolean), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: boolean) Stage: Stage-0 Fetch Operator @@ -530,7 +522,7 @@ POSTHOOK: Input: default@src 199 val_199 199 val_199 2 val_2 -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from src b @@ -554,96 +546,92 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((value > 'val_2') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Filter Operator + predicate: ((value > 'val_2') and key is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + residual filter predicates: {(_col3 > _col0)} {(_col1 <> _col4)} + Statistics: Num rows: 41500 Data size: 14940000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 is null (type: boolean) + Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: Group By Operator - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: true (type: boolean), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: boolean), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - residual filter predicates: {(_col3 > _col0)} {(_col1 <> _col4)} - Statistics: Num rows: 41500 Data size: 14940000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Select Operator + expressions: true (type: boolean), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: boolean), _col1 (type: string), _col2 (type: string) Stage: Stage-0 Fetch Operator @@ -651,7 +639,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from src b where not exists @@ -674,8 +662,8 @@ POSTHOOK: Input: default@src #### A masked pattern was here #### 98 val_98 98 val_98 -Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -Warning: Shuffle Join JOIN[14][tables = [$hdt$_3, $hdt$_4]] in Stage 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product PREHOOK: query: explain SELECT p1.p_name FROM part p1 LEFT JOIN (select p_type as p_col from part ) p2 WHERE NOT EXISTS (select pp1.p_type as p_col from part pp1 where pp1.p_partkey = p2.p_col) PREHOOK: type: QUERY @@ -688,255 +676,226 @@ POSTHOOK: Input: default@part #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-6 is a root stage - Stage-7 depends on stages: Stage-6 - Stage-4 depends on stages: Stage-7 - Stage-5 depends on stages: Stage-4 - Stage-0 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - alias: part - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_type (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 676 Data size: 152100 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 676 Data size: 152100 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1014 Data size: 124050 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 676 Data size: 82700 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 676 Data size: 81796 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 676 Data size: 81796 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: p1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: part - filterExpr: (UDFToDouble(p_type) is not null and p_type is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(p_type) is not null and p_type is not null) (type: boolean) - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_type (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 4 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) + Reducer 5 <- Map 10 (XPROD_EDGE), Map 4 (XPROD_EDGE) + Reducer 6 <- Reducer 5 (SIMPLE_EDGE) + Reducer 7 <- Map 9 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: p_name (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 10 + Map Operator Tree: + TableScan + alias: p1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: part Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col1 - Statistics: Num rows: 676 Data size: 70304 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: pp1 - filterExpr: UDFToDouble(p_partkey) is not null (type: boolean) - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: UDFToDouble(p_partkey) is not null (type: boolean) - Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToDouble(p_partkey) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: p_type (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Filter Operator + predicate: (UDFToDouble(p_type) is not null and p_type is not null) (type: boolean) + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: p_type (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 9 + Map Operator Tree: + TableScan + alias: pp1 + filterExpr: UDFToDouble(p_partkey) is not null (type: boolean) + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: UDFToDouble(p_partkey) is not null (type: boolean) + Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: UDFToDouble(p_partkey) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 676 Data size: 152100 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: double) + key expressions: _col1 (type: string) null sort order: z sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Reduce Output Operator - key expressions: _col1 (type: double) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: double) - Statistics: Num rows: 24 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: double) - 1 _col1 (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 676 Data size: 152100 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1014 Data size: 124050 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 is null (type: boolean) + Statistics: Num rows: 676 Data size: 82700 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 676 Data size: 81796 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 676 Data size: 81796 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1 + Statistics: Num rows: 676 Data size: 70304 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: string) + minReductionHashAggr: 0.964497 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 24 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: double) + Statistics: Num rows: 24 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: double) + 1 _col1 (type: double) + outputColumnNames: _col1 + Statistics: Num rows: 24 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 8 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1248 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: true (type: boolean), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: boolean) Stage: Stage-0 Fetch Operator @@ -944,8 +903,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -Warning: Shuffle Join JOIN[14][tables = [$hdt$_3, $hdt$_4]] in Stage 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product PREHOOK: query: SELECT p1.p_name FROM part p1 LEFT JOIN (select p_type as p_col from part ) p2 WHERE NOT EXISTS (select pp1.p_type as p_col from part pp1 where pp1.p_partkey = p2.p_col) PREHOOK: type: QUERY @@ -956,682 +915,682 @@ POSTHOOK: query: SELECT p1.p_name FROM part p1 LEFT JOIN (select p_type as p_col POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### -almond antique metallic orange dim -almond aquamarine midnight light salmon -almond antique olive coral navajo almond antique blue firebrick mint -almond antique chartreuse lavender yellow -almond aquamarine sandy cyan gainsboro -almond azure aquamarine papaya violet -almond antique forest lavender goldenrod -almond aquamarine floral ivory bisque -almond aquamarine pink moccasin thistle -almond aquamarine dodger light gainsboro -almond antique salmon chartreuse burlywood -almond antique violet turquoise frosted +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique blue firebrick mint +almond antique burnished rose metallic +almond antique burnished rose metallic +almond antique burnished rose metallic +almond antique burnished rose metallic almond antique burnished rose metallic -almond aquamarine yellow dodger mint -almond antique violet chocolate turquoise -almond antique sky peru orange -almond aquamarine rose maroon antique almond antique burnished rose metallic -almond antique chartreuse khaki white -almond antique violet mint lemon -almond azure blanched chiffon midnight -almond antique gainsboro frosted violet -almond antique misty red olive -almond aquamarine burnished black steel -almond antique medium spring khaki -almond antique salmon chartreuse burlywood -almond antique blue firebrick mint -almond aquamarine pink moccasin thistle -almond aquamarine floral ivory bisque -almond antique gainsboro frosted violet -almond aquamarine yellow dodger mint -almond aquamarine dodger light gainsboro -almond aquamarine burnished black steel -almond azure blanched chiffon midnight -almond antique violet turquoise frosted -almond antique sky peru orange almond antique burnished rose metallic -almond antique violet chocolate turquoise -almond antique medium spring khaki -almond antique chartreuse khaki white almond antique burnished rose metallic -almond aquamarine rose maroon antique -almond aquamarine midnight light salmon -almond antique chartreuse lavender yellow -almond antique olive coral navajo -almond antique misty red olive -almond aquamarine sandy cyan gainsboro -almond antique violet mint lemon -almond azure aquamarine papaya violet -almond antique forest lavender goldenrod -almond antique metallic orange dim -almond antique salmon chartreuse burlywood -almond antique blue firebrick mint -almond antique violet chocolate turquoise almond antique burnished rose metallic -almond antique forest lavender goldenrod -almond aquamarine midnight light salmon -almond antique misty red olive -almond antique gainsboro frosted violet -almond antique olive coral navajo -almond antique metallic orange dim -almond antique chartreuse khaki white -almond aquamarine yellow dodger mint almond antique burnished rose metallic -almond aquamarine rose maroon antique -almond aquamarine dodger light gainsboro -almond antique chartreuse lavender yellow -almond aquamarine pink moccasin thistle -almond aquamarine burnished black steel -almond azure aquamarine papaya violet -almond antique violet mint lemon -almond azure blanched chiffon midnight -almond antique violet turquoise frosted -almond antique sky peru orange -almond antique medium spring khaki -almond aquamarine floral ivory bisque -almond aquamarine sandy cyan gainsboro -almond antique violet mint lemon -almond antique chartreuse lavender yellow -almond aquamarine burnished black steel -almond antique blue firebrick mint -almond antique violet chocolate turquoise almond antique burnished rose metallic -almond aquamarine rose maroon antique -almond aquamarine yellow dodger mint -almond aquamarine sandy cyan gainsboro -almond aquamarine floral ivory bisque -almond azure aquamarine papaya violet -almond antique metallic orange dim -almond antique sky peru orange almond antique burnished rose metallic -almond antique misty red olive -almond antique olive coral navajo -almond aquamarine dodger light gainsboro -almond aquamarine midnight light salmon -almond aquamarine pink moccasin thistle -almond antique violet turquoise frosted -almond antique forest lavender goldenrod -almond antique chartreuse khaki white -almond antique medium spring khaki -almond antique gainsboro frosted violet -almond azure blanched chiffon midnight -almond antique salmon chartreuse burlywood -almond azure aquamarine papaya violet -almond antique salmon chartreuse burlywood -almond aquamarine rose maroon antique -almond antique forest lavender goldenrod -almond antique metallic orange dim -almond antique blue firebrick mint -almond aquamarine pink moccasin thistle -almond aquamarine yellow dodger mint -almond aquamarine dodger light gainsboro -almond antique violet turquoise frosted -almond antique sky peru orange -almond antique violet chocolate turquoise -almond antique chartreuse khaki white almond antique burnished rose metallic -almond antique gainsboro frosted violet almond antique burnished rose metallic -almond antique violet mint lemon -almond aquamarine burnished black steel -almond antique medium spring khaki -almond antique misty red olive -almond aquamarine midnight light salmon -almond aquamarine sandy cyan gainsboro -almond antique olive coral navajo -almond antique chartreuse lavender yellow -almond azure blanched chiffon midnight -almond aquamarine floral ivory bisque -almond azure blanched chiffon midnight -almond antique blue firebrick mint -almond antique chartreuse lavender yellow -almond azure aquamarine papaya violet -almond antique chartreuse khaki white -almond aquamarine midnight light salmon -almond antique sky peru orange -almond antique misty red olive -almond aquamarine yellow dodger mint -almond antique violet mint lemon -almond aquamarine pink moccasin thistle -almond aquamarine sandy cyan gainsboro almond antique burnished rose metallic -almond antique salmon chartreuse burlywood -almond antique forest lavender goldenrod -almond antique metallic orange dim -almond antique violet turquoise frosted -almond antique violet chocolate turquoise -almond aquamarine dodger light gainsboro -almond antique gainsboro frosted violet almond antique burnished rose metallic -almond aquamarine rose maroon antique -almond antique olive coral navajo -almond antique medium spring khaki -almond aquamarine burnished black steel -almond aquamarine floral ivory bisque -almond antique metallic orange dim -almond antique violet chocolate turquoise almond antique burnished rose metallic -almond aquamarine dodger light gainsboro -almond antique forest lavender goldenrod almond antique burnished rose metallic -almond aquamarine yellow dodger mint -almond antique misty red olive -almond antique chartreuse khaki white -almond antique chartreuse lavender yellow -almond antique medium spring khaki -almond azure aquamarine papaya violet -almond aquamarine sandy cyan gainsboro -almond aquamarine floral ivory bisque -almond antique salmon chartreuse burlywood -almond aquamarine rose maroon antique -almond antique olive coral navajo -almond azure blanched chiffon midnight -almond aquamarine burnished black steel -almond aquamarine midnight light salmon -almond antique sky peru orange -almond antique violet mint lemon -almond aquamarine pink moccasin thistle -almond antique violet turquoise frosted -almond antique gainsboro frosted violet -almond antique blue firebrick mint -almond aquamarine midnight light salmon -almond azure blanched chiffon midnight -almond antique chartreuse lavender yellow -almond antique gainsboro frosted violet -almond aquamarine burnished black steel -almond antique medium spring khaki -almond antique blue firebrick mint -almond antique olive coral navajo -almond aquamarine dodger light gainsboro -almond antique violet chocolate turquoise -almond aquamarine rose maroon antique -almond antique violet turquoise frosted -almond antique forest lavender goldenrod -almond aquamarine floral ivory bisque -almond aquamarine pink moccasin thistle almond antique burnished rose metallic -almond azure aquamarine papaya violet -almond aquamarine sandy cyan gainsboro -almond antique salmon chartreuse burlywood -almond antique violet mint lemon -almond aquamarine yellow dodger mint -almond antique metallic orange dim -almond antique sky peru orange -almond antique misty red olive almond antique burnished rose metallic -almond antique chartreuse khaki white -almond antique sky peru orange -almond aquamarine floral ivory bisque -almond azure aquamarine papaya violet -almond antique olive coral navajo -almond azure blanched chiffon midnight -almond aquamarine sandy cyan gainsboro -almond antique chartreuse lavender yellow -almond aquamarine burnished black steel -almond antique medium spring khaki -almond aquamarine midnight light salmon -almond antique misty red olive -almond antique violet chocolate turquoise -almond antique chartreuse khaki white -almond antique violet mint lemon almond antique burnished rose metallic almond antique burnished rose metallic -almond aquamarine yellow dodger mint -almond aquamarine pink moccasin thistle -almond antique violet turquoise frosted -almond aquamarine dodger light gainsboro -almond antique forest lavender goldenrod -almond antique blue firebrick mint -almond antique gainsboro frosted violet -almond antique metallic orange dim -almond antique salmon chartreuse burlywood -almond aquamarine rose maroon antique -almond antique chartreuse khaki white -almond aquamarine pink moccasin thistle -almond aquamarine floral ivory bisque -almond antique sky peru orange -almond aquamarine yellow dodger mint -almond antique violet mint lemon -almond antique metallic orange dim almond antique burnished rose metallic -almond antique chartreuse lavender yellow -almond aquamarine burnished black steel -almond antique salmon chartreuse burlywood -almond antique misty red olive -almond antique violet turquoise frosted -almond antique blue firebrick mint -almond antique medium spring khaki -almond aquamarine rose maroon antique -almond azure blanched chiffon midnight -almond antique gainsboro frosted violet -almond aquamarine sandy cyan gainsboro -almond antique violet chocolate turquoise -almond aquamarine midnight light salmon -almond antique olive coral navajo -almond antique forest lavender goldenrod -almond azure aquamarine papaya violet almond antique burnished rose metallic -almond aquamarine dodger light gainsboro -almond antique salmon chartreuse burlywood -almond antique salmon chartreuse burlywood -almond antique chartreuse lavender yellow -almond aquamarine sandy cyan gainsboro -almond antique metallic orange dim -almond antique chartreuse khaki white -almond antique violet mint lemon -almond antique gainsboro frosted violet -almond antique sky peru orange -almond antique olive coral navajo -almond antique chartreuse khaki white almond antique burnished rose metallic -almond aquamarine rose maroon antique -almond antique violet mint lemon -almond azure blanched chiffon midnight -almond antique sky peru orange -almond antique gainsboro frosted violet almond antique burnished rose metallic -almond aquamarine floral ivory bisque -almond azure blanched chiffon midnight -almond aquamarine yellow dodger mint -almond aquamarine rose maroon antique -almond antique violet turquoise frosted almond antique burnished rose metallic -almond aquamarine yellow dodger mint -almond aquamarine dodger light gainsboro -almond aquamarine pink moccasin thistle -almond antique olive coral navajo -almond antique violet turquoise frosted -almond antique blue firebrick mint -almond aquamarine dodger light gainsboro -almond azure aquamarine papaya violet -almond aquamarine pink moccasin thistle -almond antique forest lavender goldenrod almond antique burnished rose metallic -almond aquamarine floral ivory bisque -almond antique forest lavender goldenrod -almond antique blue firebrick mint -almond antique metallic orange dim -almond antique violet chocolate turquoise -almond antique chartreuse lavender yellow -almond antique violet chocolate turquoise -almond aquamarine midnight light salmon -almond aquamarine burnished black steel -almond antique medium spring khaki -almond azure aquamarine papaya violet -almond aquamarine midnight light salmon -almond antique misty red olive -almond aquamarine burnished black steel -almond antique medium spring khaki -almond aquamarine sandy cyan gainsboro -almond antique misty red olive -almond antique metallic orange dim -almond aquamarine dodger light gainsboro almond antique burnished rose metallic -almond antique misty red olive -almond antique chartreuse lavender yellow -almond azure aquamarine papaya violet -almond antique salmon chartreuse burlywood -almond antique olive coral navajo -almond aquamarine burnished black steel -almond antique sky peru orange -almond aquamarine pink moccasin thistle -almond antique gainsboro frosted violet -almond antique violet chocolate turquoise -almond antique violet turquoise frosted -almond antique violet mint lemon -almond aquamarine midnight light salmon -almond azure blanched chiffon midnight -almond aquamarine rose maroon antique -almond aquamarine floral ivory bisque -almond aquamarine sandy cyan gainsboro -almond antique medium spring khaki -almond antique chartreuse khaki white -almond aquamarine yellow dodger mint -almond antique forest lavender goldenrod almond antique burnished rose metallic -almond antique blue firebrick mint -almond aquamarine dodger light gainsboro -almond antique metallic orange dim -almond aquamarine midnight light salmon -almond aquamarine burnished black steel -almond antique violet turquoise frosted -almond antique violet chocolate turquoise almond antique burnished rose metallic -almond antique forest lavender goldenrod -almond aquamarine rose maroon antique -almond antique chartreuse khaki white -almond antique sky peru orange -almond azure blanched chiffon midnight -almond antique olive coral navajo -almond antique misty red olive -almond aquamarine sandy cyan gainsboro -almond antique salmon chartreuse burlywood -almond aquamarine floral ivory bisque -almond antique blue firebrick mint almond antique burnished rose metallic -almond azure aquamarine papaya violet -almond aquamarine yellow dodger mint -almond antique violet mint lemon -almond antique medium spring khaki -almond antique chartreuse lavender yellow -almond aquamarine pink moccasin thistle -almond antique gainsboro frosted violet -almond aquamarine dodger light gainsboro -almond azure blanched chiffon midnight -almond azure blanched chiffon midnight -almond aquamarine burnished black steel -almond aquamarine burnished black steel -almond antique violet chocolate turquoise -almond antique salmon chartreuse burlywood -almond antique salmon chartreuse burlywood -almond antique blue firebrick mint -almond aquamarine floral ivory bisque -almond antique gainsboro frosted violet -almond aquamarine floral ivory bisque -almond antique gainsboro frosted violet -almond antique violet turquoise frosted -almond antique violet turquoise frosted -almond antique blue firebrick mint -almond antique forest lavender goldenrod -almond antique forest lavender goldenrod almond antique burnished rose metallic -almond antique olive coral navajo almond antique burnished rose metallic -almond antique olive coral navajo -almond aquamarine rose maroon antique -almond aquamarine yellow dodger mint -almond antique violet chocolate turquoise -almond aquamarine pink moccasin thistle -almond aquamarine yellow dodger mint -almond antique violet mint lemon -almond antique violet mint lemon -almond aquamarine pink moccasin thistle -almond aquamarine rose maroon antique -almond antique misty red olive -almond antique misty red olive -almond antique chartreuse khaki white -almond antique chartreuse khaki white -almond antique metallic orange dim almond antique burnished rose metallic -almond antique chartreuse lavender yellow -almond antique chartreuse lavender yellow -almond aquamarine midnight light salmon -almond aquamarine midnight light salmon -almond antique sky peru orange -almond antique sky peru orange -almond antique medium spring khaki -almond antique medium spring khaki almond antique burnished rose metallic -almond antique metallic orange dim -almond azure aquamarine papaya violet -almond azure aquamarine papaya violet -almond aquamarine dodger light gainsboro -almond aquamarine sandy cyan gainsboro -almond aquamarine sandy cyan gainsboro -almond antique chartreuse lavender yellow -almond aquamarine burnished black steel -almond antique gainsboro frosted violet -almond aquamarine sandy cyan gainsboro almond antique burnished rose metallic -almond antique chartreuse khaki white -almond antique violet turquoise frosted -almond antique olive coral navajo -almond aquamarine floral ivory bisque -almond antique salmon chartreuse burlywood -almond aquamarine yellow dodger mint -almond aquamarine pink moccasin thistle -almond antique sky peru orange almond antique burnished rose metallic -almond antique metallic orange dim -almond antique violet chocolate turquoise -almond aquamarine dodger light gainsboro -almond antique violet mint lemon -almond azure aquamarine papaya violet -almond aquamarine midnight light salmon -almond antique misty red olive -almond antique medium spring khaki -almond antique blue firebrick mint -almond aquamarine rose maroon antique -almond antique forest lavender goldenrod -almond azure blanched chiffon midnight -almond antique sky peru orange -almond antique metallic orange dim -almond aquamarine rose maroon antique -almond antique blue firebrick mint -almond antique forest lavender goldenrod -almond aquamarine dodger light gainsboro -almond aquamarine pink moccasin thistle -almond aquamarine yellow dodger mint -almond antique violet turquoise frosted almond antique burnished rose metallic -almond antique chartreuse khaki white -almond antique misty red olive -almond antique violet mint lemon -almond antique medium spring khaki -almond antique chartreuse lavender yellow -almond aquamarine burnished black steel -almond aquamarine midnight light salmon -almond aquamarine sandy cyan gainsboro -almond antique violet chocolate turquoise almond antique burnished rose metallic -almond azure aquamarine papaya violet -almond aquamarine floral ivory bisque -almond azure blanched chiffon midnight -almond antique olive coral navajo -almond antique gainsboro frosted violet -almond antique salmon chartreuse burlywood -almond antique gainsboro frosted violet -almond antique blue firebrick mint -almond aquamarine pink moccasin thistle -almond antique violet turquoise frosted -almond antique sky peru orange -almond antique violet mint lemon -almond aquamarine burnished black steel -almond aquamarine midnight light salmon -almond antique olive coral navajo -almond azure blanched chiffon midnight -almond antique salmon chartreuse burlywood -almond aquamarine rose maroon antique -almond azure aquamarine papaya violet -almond aquamarine floral ivory bisque -almond antique chartreuse lavender yellow -almond aquamarine sandy cyan gainsboro -almond antique misty red olive -almond antique medium spring khaki almond antique burnished rose metallic -almond antique chartreuse khaki white -almond aquamarine dodger light gainsboro -almond aquamarine yellow dodger mint almond antique burnished rose metallic -almond antique forest lavender goldenrod -almond antique metallic orange dim -almond antique violet chocolate turquoise almond antique burnished rose metallic -almond azure blanched chiffon midnight -almond antique olive coral navajo -almond aquamarine floral ivory bisque -almond azure aquamarine papaya violet -almond aquamarine midnight light salmon -almond aquamarine sandy cyan gainsboro -almond antique chartreuse lavender yellow -almond aquamarine burnished black steel -almond antique gainsboro frosted violet -almond antique medium spring khaki -almond antique misty red olive -almond antique violet mint lemon -almond antique sky peru orange -almond antique chartreuse khaki white -almond antique violet chocolate turquoise almond antique burnished rose metallic -almond antique violet turquoise frosted -almond aquamarine yellow dodger mint -almond aquamarine pink moccasin thistle -almond aquamarine dodger light gainsboro -almond antique forest lavender goldenrod -almond antique blue firebrick mint -almond antique metallic orange dim -almond antique salmon chartreuse burlywood -almond aquamarine rose maroon antique almond antique burnished rose metallic -almond aquamarine midnight light salmon -almond antique sky peru orange -almond antique salmon chartreuse burlywood almond antique burnished rose metallic -almond aquamarine yellow dodger mint -almond antique metallic orange dim -almond antique chartreuse lavender yellow -almond antique violet turquoise frosted -almond aquamarine sandy cyan gainsboro -almond antique medium spring khaki -almond antique violet chocolate turquoise -almond antique olive coral navajo -almond aquamarine rose maroon antique -almond aquamarine burnished black steel -almond antique misty red olive -almond aquamarine pink moccasin thistle -almond aquamarine floral ivory bisque -almond antique gainsboro frosted violet -almond antique forest lavender goldenrod -almond aquamarine dodger light gainsboro -almond azure aquamarine papaya violet -almond azure blanched chiffon midnight -almond antique violet mint lemon -almond antique blue firebrick mint -almond antique chartreuse khaki white -almond azure blanched chiffon midnight -almond antique metallic orange dim -almond aquamarine pink moccasin thistle -almond aquamarine yellow dodger mint -almond aquamarine rose maroon antique almond antique burnished rose metallic almond antique burnished rose metallic -almond antique salmon chartreuse burlywood -almond aquamarine floral ivory bisque -almond aquamarine burnished black steel -almond antique medium spring khaki -almond antique chartreuse lavender yellow -almond aquamarine midnight light salmon -almond antique gainsboro frosted violet -almond aquamarine sandy cyan gainsboro -almond azure aquamarine papaya violet -almond aquamarine dodger light gainsboro -almond antique violet turquoise frosted -almond antique forest lavender goldenrod -almond antique chartreuse khaki white -almond antique misty red olive -almond antique olive coral navajo -almond antique violet mint lemon -almond antique blue firebrick mint -almond antique violet chocolate turquoise -almond antique sky peru orange -almond aquamarine sandy cyan gainsboro -almond aquamarine floral ivory bisque -almond antique chartreuse lavender yellow -almond antique metallic orange dim -almond aquamarine dodger light gainsboro almond antique burnished rose metallic -almond aquamarine pink moccasin thistle -almond aquamarine rose maroon antique -almond azure aquamarine papaya violet -almond antique chartreuse khaki white -almond aquamarine yellow dodger mint -almond antique olive coral navajo -almond antique violet chocolate turquoise -almond antique salmon chartreuse burlywood -almond antique blue firebrick mint -almond antique forest lavender goldenrod -almond antique sky peru orange -almond aquamarine burnished black steel almond antique burnished rose metallic -almond azure blanched chiffon midnight -almond antique medium spring khaki -almond antique misty red olive -almond antique violet turquoise frosted -almond antique gainsboro frosted violet -almond aquamarine midnight light salmon -almond antique violet mint lemon almond antique burnished rose metallic -almond aquamarine midnight light salmon -almond antique chartreuse lavender yellow -almond aquamarine sandy cyan gainsboro -almond aquamarine burnished black steel -almond antique violet mint lemon -almond antique misty red olive -almond antique medium spring khaki -almond antique salmon chartreuse burlywood -almond antique sky peru orange almond antique burnished rose metallic almond antique chartreuse khaki white -almond antique violet turquoise frosted -almond aquamarine yellow dodger mint -almond aquamarine dodger light gainsboro -almond antique violet chocolate turquoise -almond aquamarine pink moccasin thistle -almond antique blue firebrick mint -almond aquamarine rose maroon antique -almond antique forest lavender goldenrod -almond azure aquamarine papaya violet -almond antique gainsboro frosted violet -almond antique metallic orange dim -almond azure blanched chiffon midnight -almond aquamarine floral ivory bisque -almond antique olive coral navajo -almond aquamarine rose maroon antique -almond antique olive coral navajo -almond antique violet chocolate turquoise almond antique chartreuse khaki white -almond antique violet mint lemon -almond aquamarine midnight light salmon -almond azure blanched chiffon midnight -almond antique blue firebrick mint -almond antique burnished rose metallic -almond aquamarine dodger light gainsboro -almond antique misty red olive -almond aquamarine floral ivory bisque -almond antique metallic orange dim -almond aquamarine yellow dodger mint -almond antique medium spring khaki +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse khaki white +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow +almond antique chartreuse lavender yellow almond antique chartreuse lavender yellow -almond aquamarine pink moccasin thistle -almond aquamarine sandy cyan gainsboro -almond antique salmon chartreuse burlywood -almond antique violet turquoise frosted -almond antique burnished rose metallic almond antique forest lavender goldenrod -almond antique gainsboro frosted violet -almond aquamarine burnished black steel -almond azure aquamarine papaya violet -almond antique sky peru orange -almond aquamarine floral ivory bisque -almond antique chartreuse khaki white -almond antique misty red olive -almond aquamarine burnished black steel -almond antique sky peru orange -almond aquamarine dodger light gainsboro -almond antique violet mint lemon -almond antique medium spring khaki almond antique forest lavender goldenrod -almond antique metallic orange dim -almond antique burnished rose metallic +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod +almond antique forest lavender goldenrod almond antique gainsboro frosted violet -almond azure aquamarine papaya violet -almond antique blue firebrick mint -almond antique chartreuse lavender yellow -almond antique olive coral navajo -almond antique violet chocolate turquoise -almond azure blanched chiffon midnight -almond aquamarine midnight light salmon -almond antique violet turquoise frosted -almond aquamarine yellow dodger mint -almond aquamarine pink moccasin thistle -almond antique burnished rose metallic -almond aquamarine rose maroon antique -almond aquamarine sandy cyan gainsboro -almond antique salmon chartreuse burlywood +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique gainsboro frosted violet +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique medium spring khaki +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique metallic orange dim +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique misty red olive +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique olive coral navajo +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique salmon chartreuse burlywood +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique sky peru orange +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet chocolate turquoise +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet mint lemon +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond antique violet turquoise frosted +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine burnished black steel +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine dodger light gainsboro +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine floral ivory bisque +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine midnight light salmon +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine pink moccasin thistle +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine rose maroon antique +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine sandy cyan gainsboro +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond aquamarine yellow dodger mint +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure aquamarine papaya violet +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight +almond azure blanched chiffon midnight PREHOOK: query: create table tschema(id int, name string,dept string) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default diff --git ql/src/test/results/clientpositive/llap/subquery_notexists_having.q.out ql/src/test/results/clientpositive/llap/subquery_notexists_having.q.out new file mode 100644 index 0000000000..ec12ce707b --- /dev/null +++ ql/src/test/results/clientpositive/llap/subquery_notexists_having.q.out @@ -0,0 +1,357 @@ +PREHOOK: query: explain +select * +from src b +group by key, value +having not exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_12' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select * +from src b +group by key, value +having not exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_12' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((value > 'val_12') and key is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((value > 'val_12') and key is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string), value (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: true (type: boolean), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE + Dummy Store + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 333 Data size: 59610 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 is null (type: boolean) + Statistics: Num rows: 250 Data size: 44752 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * +from src b +group by key, value +having not exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_12' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * +from src b +group by key, value +having not exists + (select a.key + from src a + where b.value = a.value and a.key = b.key and a.value > 'val_12' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 +10 val_10 +100 val_100 +103 val_103 +104 val_104 +105 val_105 +11 val_11 +111 val_111 +113 val_113 +114 val_114 +116 val_116 +118 val_118 +119 val_119 +12 val_12 +PREHOOK: query: explain +select * +from src b +group by key, value +having not exists + (select distinct a.key + from src a + where b.value = a.value and a.value > 'val_12' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select * +from src b +group by key, value +having not exists + (select distinct a.key + from src a + where b.value = a.value and a.value > 'val_12' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: value (type: string), key (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (value > 'val_12') (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: value (type: string), key (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 291 Data size: 51966 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col2 is null (type: boolean) + Statistics: Num rows: 250 Data size: 44644 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col1 (type: string) + mode: complete + outputColumnNames: _col0 + Statistics: Num rows: 41 Data size: 3731 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: true (type: boolean), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: boolean) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * +from src b +group by key, value +having not exists + (select distinct a.key + from src a + where b.value = a.value and a.value > 'val_12' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * +from src b +group by key, value +having not exists + (select distinct a.key + from src a + where b.value = a.value and a.value > 'val_12' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 +10 val_10 +100 val_100 +103 val_103 +104 val_104 +105 val_105 +11 val_11 +111 val_111 +113 val_113 +114 val_114 +116 val_116 +118 val_118 +119 val_119 +12 val_12 diff --git ql/src/test/results/clientpositive/llap/subquery_notin_having.q.out ql/src/test/results/clientpositive/llap/subquery_notin_having.q.out new file mode 100644 index 0000000000..5980181eee --- /dev/null +++ ql/src/test/results/clientpositive/llap/subquery_notin_having.q.out @@ -0,0 +1,1119 @@ +Warning: Shuffle Join MERGEJOIN[40][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain +select key, count(*) +from src +group by key +having key not in + ( select key from src s1 + where s1.key > '12' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select key, count(*) +from src +group by key +having key not in + ( select key from src s1 + where s1.key > '12' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 4 (XPROD_EDGE) + Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Filter Operator + predicate: (key > '12') (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(key) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: s1 + filterExpr: (key > '12') (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (key > '12') (type: boolean) + Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE + Dummy Store + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 333 Data size: 31971 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 333 Data size: 31971 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: boolean) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col4, _col5 + Statistics: Num rows: 333 Data size: 37299 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 333 Data size: 37299 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col2 = 0L) or (_col5 is null and (_col3 >= _col2) and _col0 is not null)) (type: boolean) + Statistics: Num rows: 333 Data size: 37299 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 333 Data size: 31635 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 31635 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a + where min(p_retailprice) = l and r - l > 600 + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@part +#### A masked pattern was here #### +POSTHOOK: query: explain +select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a + where min(p_retailprice) = l and r - l > 600 + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@part +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 5 <- Map 1 (SIMPLE_EDGE) + Reducer 6 <- Reducer 5 (SIMPLE_EDGE) + Reducer 7 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: p_mfgr (type: string), p_retailprice (type: double) + outputColumnNames: p_mfgr, p_retailprice + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(p_retailprice) + keys: p_mfgr (type: string) + minReductionHashAggr: 0.8076923 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: double) + Group By Operator + aggregations: min(p_retailprice), max(p_retailprice) + keys: p_mfgr (type: string) + minReductionHashAggr: 0.8076923 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: double), _col2 (type: double) + Filter Operator + predicate: p_mfgr is not null (type: boolean) + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(p_retailprice), max(p_retailprice) + keys: p_mfgr (type: string) + minReductionHashAggr: 0.8076923 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: double), _col2 (type: double) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: double) + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: double) + 1 _col0 (type: double) + outputColumnNames: _col0, _col1, _col3, _col4 + Statistics: Num rows: 6 Data size: 668 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: double) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: double) + Statistics: Num rows: 6 Data size: 668 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: bigint), _col4 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: double) + 1 _col0 (type: string), _col2 (type: double) + outputColumnNames: _col0, _col1, _col3, _col4, _col6 + Statistics: Num rows: 7 Data size: 798 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col3 is null or (_col3 = 0L) or (_col6 is not null or _col0 is null or (_col4 < _col3)) is not true) (type: boolean) + Statistics: Num rows: 7 Data size: 798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7 Data size: 742 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 7 Data size: 742 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((_col2 - _col1) > 600.0D) and _col1 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(_col0) + keys: _col1 (type: double) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + Reducer 7 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((_col2 - _col1) > 600.0D) and _col1 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), true (type: boolean), _col1 (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: double) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: double) + Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: boolean) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a + where min(p_retailprice) = l and r - l > 600 + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@part +#### A masked pattern was here #### +POSTHOOK: query: select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a + where min(p_retailprice) = l and r - l > 600 + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@part +#### A masked pattern was here #### +Manufacturer#1 1173.15 +Manufacturer#2 1690.68 +Warning: Shuffle Join MERGEJOIN[45][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain +select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from part a + group by p_mfgr + having max(p_retailprice) - min(p_retailprice) > 600 + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@part +#### A masked pattern was here #### +POSTHOOK: query: explain +select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from part a + group by p_mfgr + having max(p_retailprice) - min(p_retailprice) > 600 + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@part +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 5 (XPROD_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: p_mfgr (type: string), p_retailprice (type: double) + outputColumnNames: p_mfgr, p_retailprice + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(p_retailprice) + keys: p_mfgr (type: string) + minReductionHashAggr: 0.8076923 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: double) + Group By Operator + aggregations: max(p_retailprice), min(p_retailprice) + keys: p_mfgr (type: string) + minReductionHashAggr: 0.8076923 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: double), _col2 (type: double) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: a + filterExpr: p_mfgr is not null (type: boolean) + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: p_mfgr is not null (type: boolean) + Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: max(p_retailprice), min(p_retailprice) + keys: p_mfgr (type: string) + minReductionHashAggr: 0.8076923 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: double), _col2 (type: double) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0), min(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col1 - _col2) > 600.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE + Dummy Store + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 6 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 6 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: double), _col3 (type: boolean) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col4, _col5 + Statistics: Num rows: 6 Data size: 740 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 6 Data size: 740 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col2 = 0L) or (_col5 is null and (_col3 >= _col2) and _col0 is not null)) (type: boolean) + Statistics: Num rows: 6 Data size: 740 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 636 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 6 Data size: 636 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: max(VALUE._col0), min(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col1 - _col2) > 600.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(_col0) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[45][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from part a + group by p_mfgr + having max(p_retailprice) - min(p_retailprice) > 600 + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@part +#### A masked pattern was here #### +POSTHOOK: query: select b.p_mfgr, min(p_retailprice) +from part b +group by b.p_mfgr +having b.p_mfgr not in + (select p_mfgr + from part a + group by p_mfgr + having max(p_retailprice) - min(p_retailprice) > 600 + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@part +#### A masked pattern was here #### +Manufacturer#2 1690.68 +Manufacturer#1 1173.15 +PREHOOK: query: CREATE TABLE t1_n145 (c1 INT, c2 CHAR(100)) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t1_n145 +POSTHOOK: query: CREATE TABLE t1_n145 (c1 INT, c2 CHAR(100)) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1_n145 +PREHOOK: query: INSERT INTO t1_n145 VALUES (null,null), (1,''), (2,'abcde'), (100,'abcdefghij') +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t1_n145 +POSTHOOK: query: INSERT INTO t1_n145 VALUES (null,null), (1,''), (2,'abcde'), (100,'abcdefghij') +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t1_n145 +POSTHOOK: Lineage: t1_n145.c1 SCRIPT [] +POSTHOOK: Lineage: t1_n145.c2 SCRIPT [] +PREHOOK: query: CREATE TABLE t2_n85 (c1 INT) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t2_n85 +POSTHOOK: query: CREATE TABLE t2_n85 (c1 INT) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t2_n85 +PREHOOK: query: INSERT INTO t2_n85 VALUES (null), (2), (100) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t2_n85 +POSTHOOK: query: INSERT INTO t2_n85 VALUES (null), (2), (100) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t2_n85 +POSTHOOK: Lineage: t2_n85.c1 SCRIPT [] +Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n145 +PREHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +POSTHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n145 +POSTHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 6 (XPROD_EDGE) + Reducer 6 <- Map 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n145 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: int) + outputColumnNames: c1 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: c1 (type: int) + minReductionHashAggr: 0.25 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: t2_n85 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: c1 (type: int) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: int) + outputColumnNames: c1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(c1) + minReductionHashAggr: 0.6666666 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Dummy Store + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: boolean) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col2, _col3, _col4 + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col4 + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col1 = 0L) or (_col4 is null and (_col2 >= _col1) and _col0 is not null)) (type: boolean) + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +PREHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n145 +PREHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +POSTHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n145 +POSTHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +PREHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n145 +PREHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +POSTHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n145 +POSTHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1_n145 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: c1 (type: int) + outputColumnNames: c1 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: c1 (type: int) + minReductionHashAggr: 0.25 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: c1 (type: int) + minReductionHashAggr: 0.6666666 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: t2_n85 + filterExpr: c1 is not null (type: boolean) + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: c1 is not null (type: boolean) + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(c1) + keys: c1 (type: int) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + Group By Operator + keys: c1 (type: int) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Dummy Store + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3 + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: bigint), _col3 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col0, _col2, _col3, _col5 + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col2 is null or (_col2 = 0L) or (_col5 is not null or _col0 is null or (_col3 < _col2)) is not true) (type: boolean) + Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Dummy Store + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + null sort order: z + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: boolean) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) +PREHOOK: type: QUERY +PREHOOK: Input: default@t1_n145 +PREHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +POSTHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1_n145 +POSTHOOK: Input: default@t2_n85 +#### A masked pattern was here #### +1 +NULL +PREHOOK: query: DROP TABLE t1_n145 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t1_n145 +PREHOOK: Output: default@t1_n145 +POSTHOOK: query: DROP TABLE t1_n145 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t1_n145 +POSTHOOK: Output: default@t1_n145 +PREHOOK: query: DROP TABLE t2_n85 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@t2_n85 +PREHOOK: Output: default@t2_n85 +POSTHOOK: query: DROP TABLE t2_n85 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@t2_n85 +POSTHOOK: Output: default@t2_n85 diff --git ql/src/test/results/clientpositive/llap/subquery_unqual_corr_expr.q.out ql/src/test/results/clientpositive/llap/subquery_unqual_corr_expr.q.out new file mode 100644 index 0000000000..0d8e3f1bcb --- /dev/null +++ ql/src/test/results/clientpositive/llap/subquery_unqual_corr_expr.q.out @@ -0,0 +1,274 @@ +PREHOOK: query: explain +select * from src tablesample (10 rows) where lower(key) in (select key from src) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from src tablesample (10 rows) where lower(key) in (select key from src) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + filterExpr: lower(key) is not null (type: boolean) + Row Limit Per Split: 10 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: lower(key) is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: lower(key) (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: lower(key) (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: key (type: string), value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 lower(key) (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select * from src tablesample (10 rows) where lower(key) in (select key from src) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * from src tablesample (10 rows) where lower(key) in (select key from src) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +165 val_165 +238 val_238 +255 val_255 +27 val_27 +278 val_278 +311 val_311 +409 val_409 +484 val_484 +86 val_86 +98 val_98 +Warning: Shuffle Join MERGEJOIN[28][tables = [src, sq_1_notin_nullcheck]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: explain +select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Reducer 5 (XPROD_EDGE) + Reducer 3 <- Map 4 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Row Limit Per Split: 10 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: key (type: string), value (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is null (type: boolean) + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: concat(_col0, _col1) (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: concat(_col0, _col1) (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col1 (type: string) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 concat(_col0, _col1) (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col5 + Statistics: Num rows: 684 Data size: 165339 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: _col5 is null (type: boolean) + Statistics: Num rows: 184 Data size: 44584 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 184 Data size: 44584 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 184 Data size: 44584 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col0 = 0L) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: 0L (type: bigint) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[28][tables = [src, sq_1_notin_nullcheck]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +165 val_165 +238 val_238 +255 val_255 +278 val_278 +27 val_27 +311 val_311 +409 val_409 +484 val_484 +86 val_86 +98 val_98 diff --git ql/src/test/results/clientpositive/llap/subquery_unqualcolumnrefs.q.out ql/src/test/results/clientpositive/llap/subquery_unqualcolumnrefs.q.out new file mode 100644 index 0000000000..e50bfc9f22 --- /dev/null +++ ql/src/test/results/clientpositive/llap/subquery_unqualcolumnrefs.q.out @@ -0,0 +1,605 @@ +PREHOOK: query: create table src11_n0 (key1 string, value1 string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@src11_n0 +POSTHOOK: query: create table src11_n0 (key1 string, value1 string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src11_n0 +PREHOOK: query: create table part2_n2( + p2_partkey INT, + p2_name STRING, + p2_mfgr STRING, + p2_brand STRING, + p2_type STRING, + p2_size INT, + p2_container STRING, + p2_retailprice DOUBLE, + p2_comment STRING +) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@part2_n2 +POSTHOOK: query: create table part2_n2( + p2_partkey INT, + p2_name STRING, + p2_mfgr STRING, + p2_brand STRING, + p2_type STRING, + p2_size INT, + p2_container STRING, + p2_retailprice DOUBLE, + p2_comment STRING +) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@part2_n2 +PREHOOK: query: explain select * from src11_n0 where src11_n0.key1 in (select key from src where src11_n0.value1 = value and key > '9') +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src11_n0 +#### A masked pattern was here #### +POSTHOOK: query: explain select * from src11_n0 where src11_n0.key1 in (select key from src where src11_n0.value1 = value and key > '9') +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src11_n0 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src11_n0 + filterExpr: ((key1 > '9') and value1 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key1 > '9') and value1 is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key1 (type: string), value1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 91 Data size: 16251 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 91 Data size: 16251 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select * from src a where a.key in (select key from src where a.value = value and key > '9') +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain select * from src a where a.key in (select key from src where a.value = value and key > '9') +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + filterExpr: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select * +from src b +where b.key in + (select distinct key + from src + where b.value = value and key > '9' + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: explain +select * +from src b +where b.key in + (select distinct key + from src + where b.value = value and key > '9' + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + filterExpr: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src + filterExpr: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((key > '9') and value is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Semi Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select p_mfgr, b.p_name, p_size +from part b +where b.p_name not in + (select p_name + from (select p_mfgr, p_name, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a + where r <= 2 and b.p_mfgr = p_mfgr + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@part +#### A masked pattern was here #### +POSTHOOK: query: explain +select p_mfgr, b.p_name, p_size +from part b +where b.p_name not in + (select p_name + from (select p_mfgr, p_name, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a + where r <= 2 and b.p_mfgr = p_mfgr + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@part +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 6 <- Map 1 (SIMPLE_EDGE) + Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: string), _col2 (type: int) + Filter Operator + predicate: p_mfgr is not null (type: boolean) + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: p_mfgr (type: string), p_size (type: int) + null sort order: az + Map-reduce partition columns: p_mfgr (type: string) + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Reduce Output Operator + key expressions: p_mfgr (type: string), p_size (type: int) + null sort order: az + sort order: ++ + Map-reduce partition columns: p_mfgr (type: string) + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: p_name (type: string) + Filter Operator + predicate: p_mfgr is not null (type: boolean) + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + Top N Key Operator + sort order: ++ + keys: p_mfgr (type: string), p_size (type: int) + null sort order: az + Map-reduce partition columns: p_mfgr (type: string) + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Reduce Output Operator + key expressions: p_mfgr (type: string), p_size (type: int) + null sort order: az + sort order: ++ + Map-reduce partition columns: p_mfgr (type: string) + Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: p_name (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4, _col5 + Statistics: Num rows: 33 Data size: 7695 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 33 Data size: 7695 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: string), _col1 (type: string) + 1 _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col7 + Statistics: Num rows: 38 Data size: 8914 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (_col4 is null or (_col4 = 0L) or (_col7 is not null or _col0 is null or (_col5 < _col4)) is not true) (type: boolean) + Statistics: Num rows: 38 Data size: 8914 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 38 Data size: 8474 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 38 Data size: 8474 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 4 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: _col1, _col2, _col5 + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col1: string, _col2: string, _col5: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col5 ASC NULLS LAST + partition by: _col2 + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col5 + name: rank + window function: GenericUDAFRankEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (rank_window_0 <= 2) (type: boolean) + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(_col0) + keys: _col1 (type: string) + minReductionHashAggr: 0.5 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + Reducer 5 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + Reducer 6 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) + outputColumnNames: _col1, _col2, _col5 + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col1: string, _col2: string, _col5: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col5 ASC NULLS LAST + partition by: _col2 + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col5 + name: rank + window function: GenericUDAFRankEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((rank_window_0 <= 2) and _col1 is not null) (type: boolean) + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 7 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), true (type: boolean), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: boolean) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + diff --git ql/src/test/results/clientpositive/llap/tablevalues.q.out ql/src/test/results/clientpositive/llap/tablevalues.q.out new file mode 100644 index 0000000000..cf1666db7d --- /dev/null +++ ql/src/test/results/clientpositive/llap/tablevalues.q.out @@ -0,0 +1,945 @@ +PREHOOK: query: CREATE TABLE mytbl_n1 AS +SELECT key, value +FROM src +ORDER BY key +LIMIT 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@mytbl_n1 +POSTHOOK: query: CREATE TABLE mytbl_n1 AS +SELECT key, value +FROM src +ORDER BY key +LIMIT 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@mytbl_n1 +POSTHOOK: Lineage: mytbl_n1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: mytbl_n1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: EXPLAIN +INSERT INTO mytbl_n1(key,value) +SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) +WHERE b = 9 +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@mytbl_n1 +POSTHOOK: query: EXPLAIN +INSERT INTO mytbl_n1(key,value) +SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) +WHERE b = 9 +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@mytbl_n1 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: array(const struct(1,2),const struct(3,4)) (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Filter Operator + predicate: (col2 = 9) (type: boolean) + Statistics: Num rows: 1 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: CAST( col1 AS STRING) (type: string), '9' (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mytbl_n1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + minReductionHashAggr: 0.0 + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct), _col1 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: false + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.mytbl_n1 + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.mytbl_n1 + +PREHOOK: query: INSERT INTO mytbl_n1(key,value) +SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) +WHERE b = 9 +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@mytbl_n1 +POSTHOOK: query: INSERT INTO mytbl_n1(key,value) +SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) +WHERE b = 9 +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@mytbl_n1 +POSTHOOK: Lineage: mytbl_n1.key SCRIPT [] +POSTHOOK: Lineage: mytbl_n1.value EXPRESSION [] +PREHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t + LATERAL VIEW + INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t + LATERAL VIEW + INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: mytbl_n1 + Select Operator + expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) + outputColumnNames: _col0 + UDTF Operator + function name: inline + Select Operator + expressions: col3 (type: string), col4 (type: int), col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t + LATERAL VIEW + INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t + LATERAL VIEW + INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +A 10 0 +B 20 0 +A 10 0 +B 20 0 +A 10 0 +B 20 0 +A 10 10 +B 20 10 +A 10 100 +B 20 100 +PREHOOK: query: EXPLAIN +SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Select Operator + expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) + outputColumnNames: _col0 + UDTF Operator + function name: inline + Select Operator + expressions: col1 (type: string), col2 (type: int), col3 (type: int) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +POSTHOOK: query: SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +A 10 30 +B 20 30 +PREHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30.0),('B', 20, 30.0)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30.0),('B', 20, 30.0)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Select Operator + expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) + outputColumnNames: _col0 + UDTF Operator + function name: inline + Select Operator + expressions: col1 (type: string), col2 (type: int), col3 (type: decimal(2,0)) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +A 10 30 +B 20 30 +Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + (SELECT key, value FROM mytbl_n1) t +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + (SELECT key, value FROM mytbl_n1) t +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 3 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: col1 (type: string), col2 (type: int), col3 (type: int) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: mytbl_n1 + Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + (SELECT key, value FROM mytbl_n1) t +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + (SELECT key, value FROM mytbl_n1) t +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +B 20 30 +B 20 30 +B 20 30 +B 20 30 +B 20 30 +A 10 30 +A 10 30 +A 10 30 +A 10 30 +A 10 30 +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 3 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: col1 (type: string), col2 (type: int), col3 (type: int) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: array(const struct('A',10),const struct('B',20)) (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 2440 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 2440 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), + TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +#### A masked pattern was here #### +B 20 30 +B 20 30 +A 10 30 +A 10 30 +Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (XPROD_EDGE), Map 3 (XPROD_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: mytbl_n1 + Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: col1 (type: string), col2 (type: int), col3 (type: int) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: string), _col2 (type: int), _col3 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +B 20 30 +A 10 30 +B 20 30 +A 10 30 +B 20 30 +A 10 30 +B 20 30 +A 10 30 +B 20 30 +A 10 30 +PREHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: mytbl_n1 + Select Operator + expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) + outputColumnNames: _col0 + UDTF Operator + function name: inline + Select Operator + expressions: col3 (type: string), col4 (type: int), col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + ListSink + +PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +A 10 0 +B 20 0 +A 10 0 +B 20 0 +A 10 0 +B 20 0 +A 10 10 +B 20 10 +A 10 100 +B 20 100 +PREHOOK: query: EXPLAIN +SELECT t.key +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT t.key +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: mytbl_n1 + Select Operator + expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) + outputColumnNames: _col0 + UDTF Operator + function name: inline + Select Operator + expressions: col1 (type: string) + outputColumnNames: _col0 + ListSink + +PREHOOK: query: SELECT t.key +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t.key +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +0 +0 +0 +0 +0 +0 +10 +10 +100 +100 +PREHOOK: query: EXPLAIN +SELECT tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: mytbl_n1 + Select Operator + expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) + outputColumnNames: _col0 + UDTF Operator + function name: inline + Select Operator + expressions: col5 (type: string) + outputColumnNames: _col0 + ListSink + +PREHOOK: query: SELECT tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col3 +FROM + (SELECT key, value FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +0 +0 +0 +0 +0 +0 +10 +10 +100 +100 +PREHOOK: query: EXPLAIN +SELECT tf.col3 +FROM + (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +SELECT tf.col3 +FROM + (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: mytbl_n1 + Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: 0 (type: int), key (type: string) + null sort order: az + sort order: +- + Map-reduce partition columns: 0 (type: int) + Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 1770 Basic stats: COMPLETE Column stats: COMPLETE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 DESC NULLS LAST + partition by: 0 + raw input shape: + window functions: + window function definition + alias: row_number_window_0 + name: row_number + window function: GenericUDAFRowNumberEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 5 Data size: 1770 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: array(struct(row_number_window_0,'A',10,row_number_window_0),struct(row_number_window_0,'B',20,row_number_window_0)) (type: array>) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 13400 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 5 Data size: 13400 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + expressions: col4 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT tf.col3 +FROM + (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) +PREHOOK: type: QUERY +PREHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT tf.col3 +FROM + (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, + LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@mytbl_n1 +#### A masked pattern was here #### +1 +1 +2 +2 +3 +3 +4 +4 +5 +5 diff --git ql/src/test/results/clientpositive/temp_table_add_part_multiple.q.out ql/src/test/results/clientpositive/llap/temp_table_add_part_multiple.q.out similarity index 100% rename from ql/src/test/results/clientpositive/temp_table_add_part_multiple.q.out rename to ql/src/test/results/clientpositive/llap/temp_table_add_part_multiple.q.out index d5f3fa40ac..ac040e8509 100644 --- ql/src/test/results/clientpositive/temp_table_add_part_multiple.q.out +++ ql/src/test/results/clientpositive/llap/temp_table_add_part_multiple.q.out @@ -113,7 +113,7 @@ POSTHOOK: Input: default@add_part_test_n1_temp@ds=2010-02-01 POSTHOOK: Input: default@add_part_test_n1_temp@ds=2010-03-01 POSTHOOK: Input: default@add_part_test_n1_temp@ds=2010-04-01 #### A masked pattern was here #### +100 100 2010-01-01 200 200 2010-02-01 500 400 2010-04-01 400 300 2010-03-01 -100 100 2010-01-01 diff --git ql/src/test/results/clientpositive/temp_table_alter_partition_coltype.q.out ql/src/test/results/clientpositive/llap/temp_table_alter_partition_coltype.q.out similarity index 65% rename from ql/src/test/results/clientpositive/temp_table_alter_partition_coltype.q.out rename to ql/src/test/results/clientpositive/llap/temp_table_alter_partition_coltype.q.out index f93c9bc8f8..ead9709817 100644 --- ql/src/test/results/clientpositive/temp_table_alter_partition_coltype.q.out +++ ql/src/test/results/clientpositive/llap/temp_table_alter_partition_coltype.q.out @@ -145,175 +145,184 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alter_coltype_temp - filterExpr: (ts = 6.3D) (type: boolean) - Statistics: Num rows: 50 Data size: 782 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (ts = 6.3D) (type: boolean) - Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: + Tez #### A masked pattern was here #### - Path -> Partition: + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### - Partition - base file name: ts=3.0 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - dt 100 - ts 3.0 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alter_coltype_temp + filterExpr: (ts = 6.3D) (type: boolean) + Statistics: Num rows: 50 Data size: 782 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (ts = 6.3D) (type: boolean) + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.98 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 1 - numRows 25 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 191 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + Path -> Partition: #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 0 - numRows 0 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 0 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.alter_coltype_temp - name: default.alter_coltype_temp + Partition + base file name: ts=3.0 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + dt 100 + ts 3.0 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - Partition - base file name: ts=6.30 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - dt 100 - ts 6.30 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + name default.alter_coltype_temp + numFiles 1 + numRows 25 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 191 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 1 - numRows 25 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 191 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + name default.alter_coltype_temp + numFiles 0 + numRows 0 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 0 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.alter_coltype_temp + name: default.alter_coltype_temp #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 0 - numRows 0 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 0 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.alter_coltype_temp - name: default.alter_coltype_temp - Truncated Path -> Alias: + Partition + base file name: ts=6.30 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + dt 100 + ts 6.30 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 + name default.alter_coltype_temp + numFiles 1 + numRows 25 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 191 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + name default.alter_coltype_temp + numFiles 0 + numRows 0 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 0 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.alter_coltype_temp + name: default.alter_coltype_temp + Truncated Path -> Alias: +#### A masked pattern was here #### + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -355,175 +364,184 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alter_coltype_temp - filterExpr: ((ts = 3.0D) and (100.0D = 100.0D)) (type: boolean) - Statistics: Num rows: 50 Data size: 782 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (ts = 3.0D) (type: boolean) - Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: + Tez #### A masked pattern was here #### - Path -> Partition: + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### - Partition - base file name: ts=3.0 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - dt 100 - ts 3.0 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alter_coltype_temp + filterExpr: ((ts = 3.0D) and (100.0D = 100.0D)) (type: boolean) + Statistics: Num rows: 50 Data size: 782 Basic stats: COMPLETE Column stats: COMPLETE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (ts = 3.0D) (type: boolean) + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 50 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + minReductionHashAggr: 0.98 + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col0 (type: bigint) + auto parallelism: false + Execution mode: vectorized, llap + LLAP IO: no inputs + Path -> Alias: #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 1 - numRows 25 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 191 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + Path -> Partition: #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 0 - numRows 0 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 0 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.alter_coltype_temp - name: default.alter_coltype_temp + Partition + base file name: ts=3.0 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + dt 100 + ts 3.0 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - Partition - base file name: ts=6.30 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - dt 100 - ts 6.30 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + name default.alter_coltype_temp + numFiles 1 + numRows 25 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 191 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 1 - numRows 25 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 191 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 216 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types string:string + name default.alter_coltype_temp + numFiles 0 + numRows 0 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 0 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.alter_coltype_temp + name: default.alter_coltype_temp #### A masked pattern was here #### - name default.alter_coltype_temp - numFiles 0 - numRows 0 - partition_columns dt/ts - partition_columns.types string:double - rawDataSize 0 - serialization.ddl struct alter_coltype_temp { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.alter_coltype_temp - name: default.alter_coltype_temp - Truncated Path -> Alias: + Partition + base file name: ts=6.30 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + dt 100 + ts 6.30 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 + name default.alter_coltype_temp + numFiles 1 + numRows 25 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 191 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 216 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns key,value + columns.comments + columns.types string:string #### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + name default.alter_coltype_temp + numFiles 0 + numRows 0 + partition_columns dt/ts + partition_columns.types string:double + rawDataSize 0 + serialization.ddl struct alter_coltype_temp { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 0 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.alter_coltype_temp + name: default.alter_coltype_temp + Truncated Path -> Alias: +#### A masked pattern was here #### + Reducer 2 + Execution mode: vectorized, llap + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + bucketingVersion: 2 + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0 + columns.types bigint + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-0 Fetch Operator @@ -720,12 +738,10 @@ STAGE PLANS: TableScan alias: alter_coltype_temp filterExpr: dt is not null (type: boolean) - Statistics: Num rows: 50 Data size: 27632 Basic stats: COMPLETE Column stats: PARTIAL GatherStats: false Select Operator expressions: key (type: string), value (type: string), dt (type: string), ts (type: double) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 50 Data size: 27632 Basic stats: COMPLETE Column stats: PARTIAL ListSink PREHOOK: query: select count(*) from alter_coltype_temp where ts = 3.0 @@ -926,12 +942,10 @@ STAGE PLANS: TableScan alias: alterdynamic_part_table_temp filterExpr: ((partcol1 = 1) and (partcol2 = '1')) (type: boolean) - Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: intcol (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: explain extended select intcol from pt.alterdynamic_part_table_temp where (partcol1='2' and partcol2='1')or (partcol1='1' and partcol2='__HIVE_DEFAULT_PARTITION__') @@ -1009,12 +1023,10 @@ STAGE PLANS: TableScan alias: alterdynamic_part_table_temp filterExpr: (struct(partcol1,partcol2)) IN (const struct(2,'1'), const struct(1,'__HIVE_DEFAULT_PARTITION__')) (type: boolean) - Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: intcol (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: NONE ListSink PREHOOK: query: select intcol from pt.alterdynamic_part_table_temp where (partcol1='2' and partcol2='1')or (partcol1='1' and partcol2='__HIVE_DEFAULT_PARTITION__') diff --git ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out ql/src/test/results/clientpositive/llap/temp_table_display_colstats_tbllvl.q.out similarity index 69% rename from ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out rename to ql/src/test/results/clientpositive/llap/temp_table_display_colstats_tbllvl.q.out index 436af6b269..29fb49bdbd 100644 --- ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out +++ ql/src/test/results/clientpositive/llap/temp_table_display_colstats_tbllvl.q.out @@ -166,45 +166,55 @@ POSTHOOK: Output: default@uservisits_web_text_none #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: uservisits_web_text_none - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) - outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: uservisits_web_text_none + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) + outputColumnNames: sourceip, adrevenue, avgtimeonsite + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: Group By Operator - aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') - minReductionHashAggr: 0.99 - mode: hash + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: Column Stats Desc: @@ -226,122 +236,132 @@ POSTHOOK: Output: default@uservisits_web_text_none #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: uservisits_web_text_none - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE - Statistics Aggregation Key Prefix: default.uservisits_web_text_none/ - GatherStats: true - Select Operator - expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) - outputColumnNames: sourceip, adrevenue, avgtimeonsite - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: uservisits_web_text_none + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Statistics Aggregation Key Prefix: default.uservisits_web_text_none/ + GatherStats: true + Select Operator + expressions: sourceip (type: string), adrevenue (type: float), avgtimeonsite (type: int) + outputColumnNames: sourceip, adrevenue, avgtimeonsite + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + bucketingVersion: 2 + null sort order: + numBuckets: -1 + sort order: + Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) + auto parallelism: false + Execution mode: llap + LLAP IO: no inputs + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: uservisits_web_text_none + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + EXTERNAL TRUE + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns sourceip,desturl,visitdate,adrevenue,useragent,ccode,lcode,skeyword,avgtimeonsite + columns.comments + columns.types string:string:string:float:string:string:string:string:int + field.delim | +#### A masked pattern was here #### + name default.uservisits_web_text_none + numFiles 1 + numRows 0 + rawDataSize 0 + serialization.ddl struct uservisits_web_text_none { string sourceip, string desturl, string visitdate, float adrevenue, string useragent, string ccode, string lcode, string skeyword, i32 avgtimeonsite} + serialization.format | + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 7060 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + EXTERNAL TRUE + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns sourceip,desturl,visitdate,adrevenue,useragent,ccode,lcode,skeyword,avgtimeonsite + columns.comments + columns.types string:string:string:float:string:string:string:string:int + field.delim | +#### A masked pattern was here #### + name default.uservisits_web_text_none + numFiles 1 + numRows 0 + rawDataSize 0 + serialization.ddl struct uservisits_web_text_none { string sourceip, string desturl, string visitdate, float adrevenue, string useragent, string ccode, string lcode, string skeyword, i32 avgtimeonsite} + serialization.format | + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 7060 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.uservisits_web_text_none + name: default.uservisits_web_text_none + Truncated Path -> Alias: +#### A masked pattern was here #### + Reducer 2 + Execution mode: llap + Needs Tagging: false + Reduce Operator Tree: Group By Operator - aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll') - minReductionHashAggr: 0.99 - mode: hash + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE + File Output Operator bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: uservisits_web_text_none - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - EXTERNAL TRUE - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns sourceip,desturl,visitdate,adrevenue,useragent,ccode,lcode,skeyword,avgtimeonsite - columns.comments - columns.types string:string:string:float:string:string:string:string:int - field.delim | -#### A masked pattern was here #### - name default.uservisits_web_text_none - numFiles 1 - numRows 0 - rawDataSize 0 - serialization.ddl struct uservisits_web_text_none { string sourceip, string desturl, string visitdate, float adrevenue, string useragent, string ccode, string lcode, string skeyword, i32 avgtimeonsite} - serialization.format | - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7060 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - EXTERNAL TRUE - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns sourceip,desturl,visitdate,adrevenue,useragent,ccode,lcode,skeyword,avgtimeonsite - columns.comments - columns.types string:string:string:float:string:string:string:string:int - field.delim | -#### A masked pattern was here #### - name default.uservisits_web_text_none - numFiles 1 - numRows 0 - rawDataSize 0 - serialization.ddl struct uservisits_web_text_none { string sourceip, string desturl, string visitdate, float adrevenue, string useragent, string ccode, string lcode, string skeyword, i32 avgtimeonsite} - serialization.format | - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 7060 - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.uservisits_web_text_none - name: default.uservisits_web_text_none - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types struct:struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 1512 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + bucketing_version -1 + columns _col0,_col1,_col2 + columns.types struct:struct:struct + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: Stats Aggregation Key Prefix: default.uservisits_web_text_none/ @@ -514,45 +534,55 @@ POSTHOOK: Output: default@empty_tab #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-0 is a root stage - Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-0 - Map Reduce - Map Operator Tree: - TableScan - alias: empty_tab - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary) - outputColumnNames: a, b, c, d, e - Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: empty_tab + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary) + outputColumnNames: a, b, c, d, e + Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll'), compute_stats(e, 'hll') + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + null sort order: + sort order: + Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: Group By Operator - aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll'), compute_stats(e, 'hll') - minReductionHashAggr: 0.99 - mode: hash + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 2192 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct), _col4 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2224 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Stage: Stage-1 + Stage: Stage-2 Stats Work Basic Stats Work: Column Stats Desc: diff --git ql/src/test/results/clientpositive/temp_table_insert1_overwrite_partitions.q.out ql/src/test/results/clientpositive/llap/temp_table_insert1_overwrite_partitions.q.out similarity index 53% rename from ql/src/test/results/clientpositive/temp_table_insert1_overwrite_partitions.q.out rename to ql/src/test/results/clientpositive/llap/temp_table_insert1_overwrite_partitions.q.out index b622f51d4c..0a92907e29 100644 --- ql/src/test/results/clientpositive/temp_table_insert1_overwrite_partitions.q.out +++ ql/src/test/results/clientpositive/llap/temp_table_insert1_overwrite_partitions.q.out @@ -46,62 +46,102 @@ POSTHOOK: Input: default@sourcetable_temp@ds=2011-11-11/hr=11 POSTHOOK: Output: default@destintable_temp@ds=2011-11-11/hr=11 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: sourcetable_temp - filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean) - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: -- + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: sourcetable_temp + filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean) + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + Top N Key Operator + sort order: -- + keys: one (type: string), two (type: string) + null sort order: zz + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + top n: 5 + Select Operator + expressions: one (type: string), two (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: -- + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.destintable_temp - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string), '11' (type: string) - outputColumnNames: one, two, ds, hr - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + Limit + Number of rows: 5 + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.destintable_temp + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string), '11' (type: string) + outputColumnNames: one, two, ds, hr + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') + keys: ds (type: string), hr (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + value expressions: _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Group By Operator - aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') - keys: ds (type: string), hr (type: string) - minReductionHashAggr: 0.99 - mode: hash + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -116,7 +156,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.destintable_temp - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -124,37 +164,6 @@ STAGE PLANS: Column Types: string, string Table: default.destintable_temp - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - value expressions: _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - PREHOOK: query: INSERT OVERWRITE TABLE destinTable_temp PARTITION (ds='2011-11-11', hr='11') if not exists SELECT one,two FROM sourceTable_temp WHERE ds='2011-11-11' AND hr='11' order by one desc, two desc limit 5 PREHOOK: type: QUERY @@ -242,44 +251,63 @@ POSTHOOK: Input: default@sourcetable_temp@ds=2011-11-11/hr=11 POSTHOOK: Output: default@destintable_temp STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: sourcetable_temp - filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean) - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: -- + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: sourcetable_temp + filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean) + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + Top N Key Operator + sort order: -- + keys: one (type: string), two (type: string) + null sort order: zz + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + top n: 5 + Select Operator + expressions: one (type: string), two (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: -- + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.destintable_temp + Limit + Number of rows: 5 + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.destintable_temp + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -291,7 +319,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.destintable_temp - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: @@ -362,62 +390,102 @@ POSTHOOK: Input: default@sourcetable_temp@ds=2011-11-11/hr=11 POSTHOOK: Output: default@destintable_temp@ds=2011-11-11/hr=11 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: sourcetable_temp - filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean) - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: -- + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: sourcetable_temp + filterExpr: ((ds = '2011-11-11') and (hr = '11')) (type: boolean) + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + Top N Key Operator + sort order: -- + keys: one (type: string), two (type: string) + null sort order: zz + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + top n: 5 + Select Operator + expressions: one (type: string), two (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: -- + Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 99 Data size: 31648 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.destintable_temp - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string), '11' (type: string) - outputColumnNames: one, two, ds, hr - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + Limit + Number of rows: 5 + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.destintable_temp + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string), '11' (type: string) + outputColumnNames: one, two, ds, hr + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') + keys: ds (type: string), hr (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE + value expressions: _col2 (type: struct), _col3 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Group By Operator - aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') - keys: ds (type: string), hr (type: string) - minReductionHashAggr: 0.99 - mode: hash + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection Stage: Stage-0 Move Operator @@ -432,7 +500,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.destintable_temp - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: @@ -440,37 +508,6 @@ STAGE PLANS: Column Types: string, string Table: default.destintable_temp - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 5 Data size: 1595 Basic stats: PARTIAL Column stats: NONE - value expressions: _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col2 (type: struct), _col3 (type: struct), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 638 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - PREHOOK: query: INSERT OVERWRITE TABLE destinTable_temp PARTITION (ds='2011-11-11', hr='11') if not exists SELECT one,two FROM sourceTable_temp WHERE ds='2011-11-11' AND hr='11' order by one desc, two desc limit 5 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/llap/temp_table_insert2_overwrite_partitions.q.out ql/src/test/results/clientpositive/llap/temp_table_insert2_overwrite_partitions.q.out new file mode 100644 index 0000000000..e56f9ebbea --- /dev/null +++ ql/src/test/results/clientpositive/llap/temp_table_insert2_overwrite_partitions.q.out @@ -0,0 +1,397 @@ +PREHOOK: query: CREATE DATABASE db1 +PREHOOK: type: CREATEDATABASE +PREHOOK: Output: database:db1 +POSTHOOK: query: CREATE DATABASE db1 +POSTHOOK: type: CREATEDATABASE +POSTHOOK: Output: database:db1 +PREHOOK: query: CREATE DATABASE db2 +PREHOOK: type: CREATEDATABASE +PREHOOK: Output: database:db2 +POSTHOOK: query: CREATE DATABASE db2 +POSTHOOK: type: CREATEDATABASE +POSTHOOK: Output: database:db2 +PREHOOK: query: CREATE TEMPORARY TABLE db1.sourceTable_temp (one string,two string) PARTITIONED BY (ds string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:db1 +PREHOOK: Output: db1@sourceTable_temp +POSTHOOK: query: CREATE TEMPORARY TABLE db1.sourceTable_temp (one string,two string) PARTITIONED BY (ds string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:db1 +POSTHOOK: Output: db1@sourceTable_temp +PREHOOK: query: load data local inpath '../../data/files/kv1.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: db1@sourcetable_temp +POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: db1@sourcetable_temp +POSTHOOK: Output: db1@sourcetable_temp@ds=2011-11-11 +PREHOOK: query: load data local inpath '../../data/files/kv3.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: db1@sourcetable_temp@ds=2011-11-11 +POSTHOOK: query: load data local inpath '../../data/files/kv3.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: db1@sourcetable_temp@ds=2011-11-11 +PREHOOK: query: CREATE TEMPORARY TABLE db2.destinTable_temp (one string,two string) PARTITIONED BY (ds string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:db2 +PREHOOK: Output: db2@destinTable_temp +POSTHOOK: query: CREATE TEMPORARY TABLE db2.destinTable_temp (one string,two string) PARTITIONED BY (ds string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:db2 +POSTHOOK: Output: db2@destinTable_temp +PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +PREHOOK: type: QUERY +PREHOOK: Input: db1@sourcetable_temp +PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 +POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: db1@sourcetable_temp +POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: sourcetable_temp + filterExpr: (ds = '2011-11-11') (type: boolean) + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + Top N Key Operator + sort order: -- + keys: one (type: string), two (type: string) + null sort order: zz + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + top n: 5 + Select Operator + expressions: one (type: string), two (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: -- + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + Limit + Number of rows: 5 + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: db2.destintable_temp + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string) + outputColumnNames: one, two, ds + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') + keys: ds (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: struct), _col2 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2011-11-11 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: db2.destintable_temp + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: one, two + Column Types: string, string + Table: db2.destintable_temp + +PREHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +PREHOOK: type: QUERY +PREHOOK: Input: db1@sourcetable_temp +PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 +POSTHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: db1@sourcetable_temp +POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 +POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).one SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:one, type:string, comment:null), ] +POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).two SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:two, type:string, comment:null), ] +PREHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc +PREHOOK: type: QUERY +PREHOOK: Input: db2@destintable_temp +PREHOOK: Input: db2@destintable_temp@ds=2011-11-11 +#### A masked pattern was here #### +POSTHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc +POSTHOOK: type: QUERY +POSTHOOK: Input: db2@destintable_temp +POSTHOOK: Input: db2@destintable_temp@ds=2011-11-11 +#### A masked pattern was here #### +98 val_98 +98 val_98 +98 val_98 +97 val_97 +97 val_97 +PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +PREHOOK: type: QUERY +PREHOOK: Input: db1@sourcetable_temp +PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 +POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: db1@sourcetable_temp +POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: sourcetable_temp + filterExpr: (ds = '2011-11-11') (type: boolean) + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + Top N Key Operator + sort order: -- + keys: one (type: string), two (type: string) + null sort order: zz + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + top n: 5 + Select Operator + expressions: one (type: string), two (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: zz + sort order: -- + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + TopN Hash Memory Usage: 0.1 + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE + Limit + Number of rows: 5 + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: db2.destintable_temp + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string) + outputColumnNames: one, two, ds + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + Group By Operator + aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') + keys: ds (type: string) + minReductionHashAggr: 0.99 + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE + value expressions: _col1 (type: struct), _col2 (type: struct) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2011-11-11 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: db2.destintable_temp + + Stage: Stage-3 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: one, two + Column Types: string, string + Table: db2.destintable_temp + +PREHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +PREHOOK: type: QUERY +PREHOOK: Input: db1@sourcetable_temp +PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 +POSTHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') + SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: db1@sourcetable_temp +POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 +POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 +POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).one SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:one, type:string, comment:null), ] +POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).two SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:two, type:string, comment:null), ] +PREHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc +PREHOOK: type: QUERY +PREHOOK: Input: db2@destintable_temp +PREHOOK: Input: db2@destintable_temp@ds=2011-11-11 +#### A masked pattern was here #### +POSTHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc +POSTHOOK: type: QUERY +POSTHOOK: Input: db2@destintable_temp +POSTHOOK: Input: db2@destintable_temp@ds=2011-11-11 +#### A masked pattern was here #### +98 val_98 +98 val_98 +98 val_98 +97 val_97 +97 val_97 +PREHOOK: query: drop table db2.destinTable_temp +PREHOOK: type: DROPTABLE +PREHOOK: Input: db2@destintable_temp +PREHOOK: Output: db2@destintable_temp +POSTHOOK: query: drop table db2.destinTable_temp +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: db2@destintable_temp +POSTHOOK: Output: db2@destintable_temp +PREHOOK: query: drop table db1.sourceTable_temp +PREHOOK: type: DROPTABLE +PREHOOK: Input: db1@sourcetable_temp +PREHOOK: Output: db1@sourcetable_temp +POSTHOOK: query: drop table db1.sourceTable_temp +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: db1@sourcetable_temp +POSTHOOK: Output: db1@sourcetable_temp +PREHOOK: query: DROP DATABASE db1 +PREHOOK: type: DROPDATABASE +PREHOOK: Input: database:db1 +PREHOOK: Output: database:db1 +POSTHOOK: query: DROP DATABASE db1 +POSTHOOK: type: DROPDATABASE +POSTHOOK: Input: database:db1 +POSTHOOK: Output: database:db1 +PREHOOK: query: DROP DATABASE db2 +PREHOOK: type: DROPDATABASE +PREHOOK: Input: database:db2 +PREHOOK: Output: database:db2 +POSTHOOK: query: DROP DATABASE db2 +POSTHOOK: type: DROPDATABASE +POSTHOOK: Input: database:db2 +POSTHOOK: Output: database:db2 diff --git ql/src/test/results/clientpositive/llap/temp_table_join1.q.out ql/src/test/results/clientpositive/llap/temp_table_join1.q.out new file mode 100644 index 0000000000..9ade6b9eb9 --- /dev/null +++ ql/src/test/results/clientpositive/llap/temp_table_join1.q.out @@ -0,0 +1,390 @@ +PREHOOK: query: CREATE TABLE src_nontemp AS SELECT * FROM src limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@src_nontemp +POSTHOOK: query: CREATE TABLE src_nontemp AS SELECT * FROM src limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_nontemp +POSTHOOK: Lineage: src_nontemp.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: src_nontemp.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: CREATE TEMPORARY TABLE src_temp AS SELECT * FROM src limit 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@src_temp +POSTHOOK: query: CREATE TEMPORARY TABLE src_temp AS SELECT * FROM src limit 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@src_temp +PREHOOK: query: EXPLAIN +FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src_nontemp +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_nontemp +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src_nontemp +#### A masked pattern was here #### +POSTHOOK: query: FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_nontemp +#### A masked pattern was here #### +165 val_165 +238 val_238 +255 val_255 +27 val_27 +278 val_278 +311 val_311 +409 val_409 +484 val_484 +86 val_86 +98 val_98 +PREHOOK: query: EXPLAIN +FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src_nontemp +PREHOOK: Input: default@src_temp +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_nontemp +POSTHOOK: Input: default@src_temp +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src_nontemp +PREHOOK: Input: default@src_temp +#### A masked pattern was here #### +POSTHOOK: query: FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_nontemp +POSTHOOK: Input: default@src_temp +#### A masked pattern was here #### +165 val_165 +238 val_238 +255 val_255 +27 val_27 +278 val_278 +311 val_311 +409 val_409 +484 val_484 +86 val_86 +98 val_98 +PREHOOK: query: EXPLAIN +FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src_temp +#### A masked pattern was here #### +POSTHOOK: query: EXPLAIN +FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_temp +#### A masked pattern was here #### +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src1 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: src2 + filterExpr: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: z + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: vectorized, llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src_temp +#### A masked pattern was here #### +POSTHOOK: query: FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) +SELECT src1.key, src2.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src_temp +#### A masked pattern was here #### +165 val_165 +238 val_238 +255 val_255 +27 val_27 +278 val_278 +311 val_311 +409 val_409 +484 val_484 +86 val_86 +98 val_98 +PREHOOK: query: DROP TABLE src_nontemp +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@src_nontemp +PREHOOK: Output: default@src_nontemp +POSTHOOK: query: DROP TABLE src_nontemp +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@src_nontemp +POSTHOOK: Output: default@src_nontemp +PREHOOK: query: DROP TABLE src_temp +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@src_temp +PREHOOK: Output: default@src_temp +POSTHOOK: query: DROP TABLE src_temp +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@src_temp +POSTHOOK: Output: default@src_temp diff --git ql/src/test/results/clientpositive/temp_table_load_dyn_part1.q.out ql/src/test/results/clientpositive/llap/temp_table_load_dyn_part1.q.out similarity index 92% rename from ql/src/test/results/clientpositive/temp_table_load_dyn_part1.q.out rename to ql/src/test/results/clientpositive/llap/temp_table_load_dyn_part1.q.out index b862b1c4fc..9503e58a59 100644 --- ql/src/test/results/clientpositive/temp_table_load_dyn_part1.q.out +++ ql/src/test/results/clientpositive/llap/temp_table_load_dyn_part1.q.out @@ -65,68 +65,57 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0 - Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-14 depends on stages: Stage-2 , consists of Stage-11, Stage-10, Stage-12 - Stage-11 - Stage-1 depends on stages: Stage-11, Stage-10, Stage-13 - Stage-9 depends on stages: Stage-1 - Stage-10 - Stage-12 - Stage-13 depends on stages: Stage-12 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-1 depends on stages: Stage-3 + Stage-5 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (ds <= '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.temp_part1_n0 - Filter Operator - predicate: (ds > '2008-04-08') (type: boolean) - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.temp_part2_n0 - Execution mode: vectorized - - Stage: Stage-8 - Conditional Operator - - Stage: Stage-5 - Move Operator - files: - hdfs directory: true + Tez #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (ds <= '2008-04-08') (type: boolean) + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.temp_part1_n0 + Filter Operator + predicate: (ds > '2008-04-08') (type: boolean) + Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 666 Data size: 241092 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.temp_part2_n0 + Execution mode: vectorized, llap + LLAP IO: no inputs + + Stage: Stage-3 + Dependency Collection Stage: Stage-0 Move Operator @@ -141,49 +130,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.temp_part1_n0 - Stage: Stage-3 + Stage: Stage-4 Stats Work Basic Stats Work: - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.temp_part1_n0 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.temp_part1_n0 - - Stage: Stage-7 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-14 - Conditional Operator - - Stage: Stage-11 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - Stage: Stage-1 Move Operator tables: @@ -197,40 +147,10 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.temp_part2_n0 - Stage: Stage-9 + Stage: Stage-5 Stats Work Basic Stats Work: - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.temp_part2_n0 - - Stage: Stage-12 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.temp_part2_n0 - - Stage: Stage-13 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - PREHOOK: query: from srcpart insert overwrite table temp_part1_n0 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08' insert overwrite table temp_part2_n0 partition(ds='2008-12-31', hr) select key, value, hr where ds > '2008-04-08' diff --git ql/src/test/results/clientpositive/mergejoins_mixed.q.out ql/src/test/results/clientpositive/mergejoins_mixed.q.out deleted file mode 100644 index 04bb90c370..0000000000 --- ql/src/test/results/clientpositive/mergejoins_mixed.q.out +++ /dev/null @@ -1,1992 +0,0 @@ -PREHOOK: query: create table a_n5 (key string, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@a_n5 -POSTHOOK: query: create table a_n5 (key string, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@a_n5 -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) left outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - TableScan - alias: c - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.key=c.key) right outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) full outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) full outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) right outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) right outer join a_n5 c on (b.value=c.key) full outer join a_n5 d on (a_n5.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - TableScan - alias: d - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (c.key=d.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@a_n5 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from a_n5 join a_n5 b on (a_n5.key=b.key) left outer join a_n5 c on (b.value=c.key) left outer join a_n5 d on (c.key=d.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@a_n5 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a_n5 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col3 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col4 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col4 (type: string) - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: string) - TableScan - alias: d - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col4 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 488 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/multi_insert_distinct.q.out ql/src/test/results/clientpositive/multi_insert_distinct.q.out deleted file mode 100644 index eefa1e1197..0000000000 --- ql/src/test/results/clientpositive/multi_insert_distinct.q.out +++ /dev/null @@ -1,567 +0,0 @@ -PREHOOK: query: CREATE TABLE tmp1 ( v1 string , v2 string , v3 string ) -ROW FORMAT DELIMITED -FIELDS TERMINATED BY '\t' -LINES TERMINATED BY '\n' -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmp1 -POSTHOOK: query: CREATE TABLE tmp1 ( v1 string , v2 string , v3 string ) -ROW FORMAT DELIMITED -FIELDS TERMINATED BY '\t' -LINES TERMINATED BY '\n' -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmp1 -PREHOOK: query: INSERT INTO tmp1 VALUES ('v1', 'v2', 'v3'), ('v1', 'v2', 'v3a') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@tmp1 -POSTHOOK: query: INSERT INTO tmp1 VALUES ('v1', 'v2', 'v3'), ('v1', 'v2', 'v3a') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@tmp1 -POSTHOOK: Lineage: tmp1.v1 SCRIPT [] -POSTHOOK: Lineage: tmp1.v2 SCRIPT [] -POSTHOOK: Lineage: tmp1.v3 SCRIPT [] -PREHOOK: query: CREATE TABLE tmp_grouped_by_all_col ( v1 string , v2 string , v3 string ) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmp_grouped_by_all_col -POSTHOOK: query: CREATE TABLE tmp_grouped_by_all_col ( v1 string , v2 string , v3 string ) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmp_grouped_by_all_col -PREHOOK: query: CREATE TABLE tmp_grouped_by_one_col ( v1 string , cnt__v2 int , cnt__v3 int ) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: query: CREATE TABLE tmp_grouped_by_one_col ( v1 string , cnt__v2 int , cnt__v3 int ) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmp_grouped_by_one_col -PREHOOK: query: CREATE TABLE tmp_grouped_by_two_col ( v1 string , v2 string , cnt__v3 int ) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: query: CREATE TABLE tmp_grouped_by_two_col ( v1 string , v2 string , cnt__v3 int ) -ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmp_grouped_by_two_col -PREHOOK: query: explain FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp1 -PREHOOK: Output: default@tmp_grouped_by_one_col -PREHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: query: explain FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp1 -POSTHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: Output: default@tmp_grouped_by_two_col -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: tmp1 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: v1 (type: string), v2 (type: string), v3 (type: string) - outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT v2), count(DISTINCT v3) - keys: v1 (type: string), v2 (type: string), v3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: v1 (type: string), v2 (type: string), v3 (type: string) - outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT v3) - keys: v1 (type: string), v2 (type: string), v3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_one_col - - Stage: Stage-0 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_one_col - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col2:0._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_two_col - - Stage: Stage-1 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_two_col - -PREHOOK: query: FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp1 -PREHOOK: Output: default@tmp_grouped_by_one_col -PREHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: query: FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(distinct v3) GROUP BY v1, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp1 -POSTHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v2 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_one_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_two_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_two_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_two_col.v2 SIMPLE [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] -PREHOOK: query: select * from tmp_grouped_by_two_col -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp_grouped_by_two_col -#### A masked pattern was here #### -POSTHOOK: query: select * from tmp_grouped_by_two_col -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp_grouped_by_two_col -#### A masked pattern was here #### -v1 v2 2 -PREHOOK: query: truncate table tmp_grouped_by_two_col -PREHOOK: type: TRUNCATETABLE -PREHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: query: truncate table tmp_grouped_by_two_col -POSTHOOK: type: TRUNCATETABLE -POSTHOOK: Output: default@tmp_grouped_by_two_col -PREHOOK: query: explain FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(v3) GROUP BY v1, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp1 -PREHOOK: Output: default@tmp_grouped_by_one_col -PREHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: query: explain FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(v3) GROUP BY v1, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp1 -POSTHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: Output: default@tmp_grouped_by_two_col -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: tmp1 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: v1 (type: string), v2 (type: string), v3 (type: string) - outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT v2), count(DISTINCT v3) - keys: v1 (type: string), v2 (type: string), v3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: v1 (type: string), v2 (type: string), v3 (type: string) - outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(v3) - keys: v1 (type: string), v2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_one_col - - Stage: Stage-0 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_one_col - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_two_col - - Stage: Stage-1 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_two_col - -PREHOOK: query: FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(v3) GROUP BY v1, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp1 -PREHOOK: Output: default@tmp_grouped_by_one_col -PREHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: query: FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_two_col -SELECT v1, v2, count(v3) GROUP BY v1, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp1 -POSTHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: Output: default@tmp_grouped_by_two_col -POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v2 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_one_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_two_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_two_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_two_col.v2 SIMPLE [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] -PREHOOK: query: select * from tmp_grouped_by_two_col -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp_grouped_by_two_col -#### A masked pattern was here #### -POSTHOOK: query: select * from tmp_grouped_by_two_col -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp_grouped_by_two_col -#### A masked pattern was here #### -v1 v2 2 -PREHOOK: query: explain FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_all_col -SELECT v1, v2, v3 GROUP BY v1, v2, v3 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp1 -PREHOOK: Output: default@tmp_grouped_by_all_col -PREHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: query: explain FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_all_col -SELECT v1, v2, v3 GROUP BY v1, v2, v3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp1 -POSTHOOK: Output: default@tmp_grouped_by_all_col -POSTHOOK: Output: default@tmp_grouped_by_one_col -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: tmp1 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: v1 (type: string), v2 (type: string), v3 (type: string) - outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT v2), count(DISTINCT v3) - keys: v1 (type: string), v2 (type: string), v3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 275 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: v1 (type: string), v2 (type: string), v3 (type: string) - outputColumnNames: v1, v2, v3 - Statistics: Num rows: 2 Data size: 518 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: v1 (type: string), v2 (type: string), v3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_one_col - - Stage: Stage-0 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_one_col - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_all_col - - Stage: Stage-1 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmp_grouped_by_all_col - -PREHOOK: query: FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_all_col -SELECT v1, v2, v3 GROUP BY v1, v2, v3 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp1 -PREHOOK: Output: default@tmp_grouped_by_all_col -PREHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: query: FROM tmp1 -INSERT INTO tmp_grouped_by_one_col -SELECT v1, count(distinct v2), count(distinct v3) GROUP BY v1 -INSERT INTO tmp_grouped_by_all_col -SELECT v1, v2, v3 GROUP BY v1, v2, v3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp1 -POSTHOOK: Output: default@tmp_grouped_by_all_col -POSTHOOK: Output: default@tmp_grouped_by_one_col -POSTHOOK: Lineage: tmp_grouped_by_all_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_all_col.v2 SIMPLE [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_all_col.v3 SIMPLE [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v2 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v2, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_one_col.cnt__v3 EXPRESSION [(tmp1)tmp1.FieldSchema(name:v3, type:string, comment:null), ] -POSTHOOK: Lineage: tmp_grouped_by_one_col.v1 SIMPLE [(tmp1)tmp1.FieldSchema(name:v1, type:string, comment:null), ] -PREHOOK: query: select * from tmp_grouped_by_all_col -PREHOOK: type: QUERY -PREHOOK: Input: default@tmp_grouped_by_all_col -#### A masked pattern was here #### -POSTHOOK: query: select * from tmp_grouped_by_all_col -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmp_grouped_by_all_col -#### A masked pattern was here #### -v1 v2 v3 -v1 v2 v3a diff --git ql/src/test/results/clientpositive/multi_insert_gby.q.out ql/src/test/results/clientpositive/multi_insert_gby.q.out deleted file mode 100644 index d36dc8de00..0000000000 --- ql/src/test/results/clientpositive/multi_insert_gby.q.out +++ /dev/null @@ -1,886 +0,0 @@ -PREHOOK: query: create table e1_n0 (key string, count int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e1_n0 -POSTHOOK: query: create table e1_n0 (key string, count int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e1_n0 -PREHOOK: query: create table e2_n1 (key string, count int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e2_n1 -POSTHOOK: query: create table e2_n1 (key string, count int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e2_n1 -PREHOOK: query: explain FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n0 -PREHOOK: Output: default@e2_n1 -POSTHOOK: query: explain FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n0 -POSTHOOK: Output: default@e2_n1 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > 500) or (key > 450)) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > 500) or (key > 450)) (type: boolean) - Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 332 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 > 450) (type: boolean) - Statistics: Num rows: 110 Data size: 9570 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n0 - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: key, count - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (KEY._col0 > 500) (type: boolean) - Statistics: Num rows: 110 Data size: 9570 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n1 - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: key, count - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n0 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, count - Column Types: string, int - Table: default.e1_n0 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, count - Column Types: string, int - Table: default.e2_n1 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n1 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n0 -PREHOOK: Output: default@e2_n1 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n0 -POSTHOOK: Output: default@e2_n1 -POSTHOOK: Lineage: e1_n0.count EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: e1_n0.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n1.count EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: e2_n1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -PREHOOK: query: select * from e1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@e1_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * from e1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e1_n0 -#### A masked pattern was here #### -452 1 -453 1 -454 3 -455 1 -457 1 -458 2 -459 2 -460 1 -462 2 -463 2 -466 3 -467 1 -468 4 -469 5 -470 1 -472 1 -475 1 -477 1 -478 2 -479 1 -480 3 -481 1 -482 1 -483 1 -484 1 -485 1 -487 1 -489 4 -490 1 -491 1 -492 2 -493 1 -494 1 -495 1 -496 1 -497 1 -498 3 -PREHOOK: query: select * from e2_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@e2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select * from e2_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e2_n1 -#### A masked pattern was here #### -PREHOOK: query: explain FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) GROUP BY key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n0 -PREHOOK: Output: default@e2_n1 -POSTHOOK: query: explain FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) GROUP BY key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n0 -POSTHOOK: Output: default@e2_n1 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-0 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n1 - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: key, count - Statistics: Num rows: 316 Data size: 28756 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (KEY._col0 > 450) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 105 Data size: 9975 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n0 - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: key, count - Statistics: Num rows: 105 Data size: 9555 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, count - Column Types: string, int - Table: default.e2_n1 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, count - Column Types: string, int - Table: default.e1_n0 - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n0 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) GROUP BY key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n0 -PREHOOK: Output: default@e2_n1 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE e1_n0 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n1 - SELECT key, COUNT(*) GROUP BY key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n0 -POSTHOOK: Output: default@e2_n1 -POSTHOOK: Lineage: e1_n0.count EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: e1_n0.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n1.count EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: e2_n1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -PREHOOK: query: select * from e1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@e1_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * from e1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e1_n0 -#### A masked pattern was here #### -452 1 -453 1 -454 3 -455 1 -457 1 -458 2 -459 2 -460 1 -462 2 -463 2 -466 3 -467 1 -468 4 -469 5 -470 1 -472 1 -475 1 -477 1 -478 2 -479 1 -480 3 -481 1 -482 1 -483 1 -484 1 -485 1 -487 1 -489 4 -490 1 -491 1 -492 2 -493 1 -494 1 -495 1 -496 1 -497 1 -498 3 -PREHOOK: query: select * from e2_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@e2_n1 -#### A masked pattern was here #### -POSTHOOK: query: select * from e2_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e2_n1 -#### A masked pattern was here #### -0 3 -10 1 -100 2 -103 2 -104 2 -105 1 -11 1 -111 1 -113 2 -114 1 -116 1 -118 2 -119 3 -12 2 -120 2 -125 2 -126 1 -128 3 -129 2 -131 1 -133 1 -134 2 -136 1 -137 2 -138 4 -143 1 -145 1 -146 2 -149 2 -15 2 -150 1 -152 2 -153 1 -155 1 -156 1 -157 1 -158 1 -160 1 -162 1 -163 1 -164 2 -165 2 -166 1 -167 3 -168 1 -169 4 -17 1 -170 1 -172 2 -174 2 -175 2 -176 2 -177 1 -178 1 -179 2 -18 2 -180 1 -181 1 -183 1 -186 1 -187 3 -189 1 -19 1 -190 1 -191 2 -192 1 -193 3 -194 1 -195 2 -196 1 -197 2 -199 3 -2 1 -20 1 -200 2 -201 1 -202 1 -203 2 -205 2 -207 2 -208 3 -209 2 -213 2 -214 1 -216 2 -217 2 -218 1 -219 2 -221 2 -222 1 -223 2 -224 2 -226 1 -228 1 -229 2 -230 5 -233 2 -235 1 -237 2 -238 2 -239 2 -24 2 -241 1 -242 2 -244 1 -247 1 -248 1 -249 1 -252 1 -255 2 -256 2 -257 1 -258 1 -26 2 -260 1 -262 1 -263 1 -265 2 -266 1 -27 1 -272 2 -273 3 -274 1 -275 1 -277 4 -278 2 -28 1 -280 2 -281 2 -282 2 -283 1 -284 1 -285 1 -286 1 -287 1 -288 2 -289 1 -291 1 -292 1 -296 1 -298 3 -30 1 -302 1 -305 1 -306 1 -307 2 -308 1 -309 2 -310 1 -311 3 -315 1 -316 3 -317 2 -318 3 -321 2 -322 2 -323 1 -325 2 -327 3 -33 1 -331 2 -332 1 -333 2 -335 1 -336 1 -338 1 -339 1 -34 1 -341 1 -342 2 -344 2 -345 1 -348 5 -35 3 -351 1 -353 2 -356 1 -360 1 -362 1 -364 1 -365 1 -366 1 -367 2 -368 1 -369 3 -37 2 -373 1 -374 1 -375 1 -377 1 -378 1 -379 1 -382 2 -384 3 -386 1 -389 1 -392 1 -393 1 -394 1 -395 2 -396 3 -397 2 -399 2 -4 1 -400 1 -401 5 -402 1 -403 3 -404 2 -406 4 -407 1 -409 3 -41 1 -411 1 -413 2 -414 2 -417 3 -418 1 -419 1 -42 2 -421 1 -424 2 -427 1 -429 2 -43 1 -430 3 -431 3 -432 1 -435 1 -436 1 -437 1 -438 3 -439 2 -44 1 -443 1 -444 1 -446 1 -448 1 -449 1 -452 1 -453 1 -454 3 -455 1 -457 1 -458 2 -459 2 -460 1 -462 2 -463 2 -466 3 -467 1 -468 4 -469 5 -47 1 -470 1 -472 1 -475 1 -477 1 -478 2 -479 1 -480 3 -481 1 -482 1 -483 1 -484 1 -485 1 -487 1 -489 4 -490 1 -491 1 -492 2 -493 1 -494 1 -495 1 -496 1 -497 1 -498 3 -5 3 -51 2 -53 1 -54 1 -57 1 -58 2 -64 1 -65 1 -66 1 -67 2 -69 1 -70 3 -72 2 -74 1 -76 2 -77 1 -78 1 -8 1 -80 1 -82 1 -83 2 -84 2 -85 1 -86 1 -87 1 -9 1 -90 3 -92 1 -95 2 -96 1 -97 2 -98 2 diff --git ql/src/test/results/clientpositive/multi_insert_gby3.q.out ql/src/test/results/clientpositive/multi_insert_gby3.q.out deleted file mode 100644 index 23518f7ac2..0000000000 --- ql/src/test/results/clientpositive/multi_insert_gby3.q.out +++ /dev/null @@ -1,2409 +0,0 @@ -PREHOOK: query: create table e1_n2 (key string, keyD double) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e1_n2 -POSTHOOK: query: create table e1_n2 (key string, keyD double) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e1_n2 -PREHOOK: query: create table e2_n3 (key string, keyD double, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e2_n3 -POSTHOOK: query: create table e2_n3 (key string, keyD double, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e2_n3 -PREHOOK: query: create table e3 (key string, keyD double) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e3 -POSTHOOK: query: create table e3 (key string, keyD double) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e3 -PREHOOK: query: explain -FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n2 -PREHOOK: Output: default@e2_n3 -POSTHOOK: query: explain -FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n2 -POSTHOOK: Output: default@e2_n3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-7 - Stage-4 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-1, Stage-4, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-5 - Stage-7 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT _col2) - keys: _col0 (type: string), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd - Column Types: string, double - Table: default.e1_n2 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd, value - Column Types: string, double, string - Table: default.e2_n3 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n3 - Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) - outputColumnNames: key, keyd, value - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n3 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n2 -PREHOOK: Output: default@e2_n3 -POSTHOOK: query: explain -FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n2 -POSTHOOK: Output: default@e2_n3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-7 - Stage-4 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-1, Stage-4, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-5 - Stage-7 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: double) - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT _col2) - keys: _col0 (type: string), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n3 - Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) - outputColumnNames: key, keyd, value - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n3 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd, value - Column Types: string, double, string - Table: default.e2_n3 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd - Column Types: string, double - Table: default.e1_n2 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n2 -PREHOOK: Output: default@e2_n3 -POSTHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n2 -POSTHOOK: Output: default@e2_n3 -POSTHOOK: Lineage: e1_n2.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e1_n2.keyd EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n3.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n3.keyd EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from e1_n2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e1_n2 -#### A masked pattern was here #### -POSTHOOK: query: select * from e1_n2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e1_n2 -#### A masked pattern was here #### -0 1.0 -10 1.0 -100 1.0 -103 1.0 -104 1.0 -105 1.0 -11 1.0 -111 1.0 -113 1.0 -114 1.0 -116 1.0 -118 1.0 -119 1.0 -12 1.0 -120 1.0 -125 1.0 -126 1.0 -128 1.0 -129 1.0 -131 1.0 -133 1.0 -134 1.0 -136 1.0 -137 1.0 -138 1.0 -143 1.0 -145 1.0 -146 1.0 -149 1.0 -15 1.0 -150 1.0 -152 1.0 -153 1.0 -155 1.0 -156 1.0 -157 1.0 -158 1.0 -160 1.0 -162 1.0 -163 1.0 -164 1.0 -165 1.0 -166 1.0 -167 1.0 -168 1.0 -169 1.0 -17 1.0 -170 1.0 -172 1.0 -174 1.0 -175 1.0 -176 1.0 -177 1.0 -178 1.0 -179 1.0 -18 1.0 -180 1.0 -181 1.0 -183 1.0 -186 1.0 -187 1.0 -189 1.0 -19 1.0 -190 1.0 -191 1.0 -192 1.0 -193 1.0 -194 1.0 -195 1.0 -196 1.0 -197 1.0 -199 1.0 -2 1.0 -20 1.0 -200 1.0 -201 1.0 -202 1.0 -203 1.0 -205 1.0 -207 1.0 -208 1.0 -209 1.0 -213 1.0 -214 1.0 -216 1.0 -217 1.0 -218 1.0 -219 1.0 -221 1.0 -222 1.0 -223 1.0 -224 1.0 -226 1.0 -228 1.0 -229 1.0 -230 1.0 -233 1.0 -235 1.0 -237 1.0 -238 1.0 -239 1.0 -24 1.0 -241 1.0 -242 1.0 -244 1.0 -247 1.0 -248 1.0 -249 1.0 -252 1.0 -255 1.0 -256 1.0 -257 1.0 -258 1.0 -26 1.0 -260 1.0 -262 1.0 -263 1.0 -265 1.0 -266 1.0 -27 1.0 -272 1.0 -273 1.0 -274 1.0 -275 1.0 -277 1.0 -278 1.0 -28 1.0 -280 1.0 -281 1.0 -282 1.0 -283 1.0 -284 1.0 -285 1.0 -286 1.0 -287 1.0 -288 1.0 -289 1.0 -291 1.0 -292 1.0 -296 1.0 -298 1.0 -30 1.0 -302 1.0 -305 1.0 -306 1.0 -307 1.0 -308 1.0 -309 1.0 -310 1.0 -311 1.0 -315 1.0 -316 1.0 -317 1.0 -318 1.0 -321 1.0 -322 1.0 -323 1.0 -325 1.0 -327 1.0 -33 1.0 -331 1.0 -332 1.0 -333 1.0 -335 1.0 -336 1.0 -338 1.0 -339 1.0 -34 1.0 -341 1.0 -342 1.0 -344 1.0 -345 1.0 -348 1.0 -35 1.0 -351 1.0 -353 1.0 -356 1.0 -360 1.0 -362 1.0 -364 1.0 -365 1.0 -366 1.0 -367 1.0 -368 1.0 -369 1.0 -37 1.0 -373 1.0 -374 1.0 -375 1.0 -377 1.0 -378 1.0 -379 1.0 -382 1.0 -384 1.0 -386 1.0 -389 1.0 -392 1.0 -393 1.0 -394 1.0 -395 1.0 -396 1.0 -397 1.0 -399 1.0 -4 1.0 -400 1.0 -401 1.0 -402 1.0 -403 1.0 -404 1.0 -406 1.0 -407 1.0 -409 1.0 -41 1.0 -411 1.0 -413 1.0 -414 1.0 -417 1.0 -418 1.0 -419 1.0 -42 1.0 -421 1.0 -424 1.0 -427 1.0 -429 1.0 -43 1.0 -430 1.0 -431 1.0 -432 1.0 -435 1.0 -436 1.0 -437 1.0 -438 1.0 -439 1.0 -44 1.0 -443 1.0 -444 1.0 -446 1.0 -448 1.0 -449 1.0 -452 1.0 -453 1.0 -454 1.0 -455 1.0 -457 1.0 -458 1.0 -459 1.0 -460 1.0 -462 1.0 -463 1.0 -466 1.0 -467 1.0 -468 1.0 -469 1.0 -47 1.0 -470 1.0 -472 1.0 -475 1.0 -477 1.0 -478 1.0 -479 1.0 -480 1.0 -481 1.0 -482 1.0 -483 1.0 -484 1.0 -485 1.0 -487 1.0 -489 1.0 -490 1.0 -491 1.0 -492 1.0 -493 1.0 -494 1.0 -495 1.0 -496 1.0 -497 1.0 -498 1.0 -5 1.0 -51 1.0 -53 1.0 -54 1.0 -57 1.0 -58 1.0 -64 1.0 -65 1.0 -66 1.0 -67 1.0 -69 1.0 -70 1.0 -72 1.0 -74 1.0 -76 1.0 -77 1.0 -78 1.0 -8 1.0 -80 1.0 -82 1.0 -83 1.0 -84 1.0 -85 1.0 -86 1.0 -87 1.0 -9 1.0 -90 1.0 -92 1.0 -95 1.0 -96 1.0 -97 1.0 -98 1.0 -PREHOOK: query: select * from e2_n3 -PREHOOK: type: QUERY -PREHOOK: Input: default@e2_n3 -#### A masked pattern was here #### -POSTHOOK: query: select * from e2_n3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e2_n3 -#### A masked pattern was here #### -0 0.0 val_0 -10 10.0 val_10 -100 200.0 val_100 -103 206.0 val_103 -104 208.0 val_104 -105 105.0 val_105 -11 11.0 val_11 -111 111.0 val_111 -113 226.0 val_113 -114 114.0 val_114 -116 116.0 val_116 -118 236.0 val_118 -119 357.0 val_119 -12 24.0 val_12 -120 240.0 val_120 -125 250.0 val_125 -126 126.0 val_126 -128 384.0 val_128 -129 258.0 val_129 -131 131.0 val_131 -133 133.0 val_133 -134 268.0 val_134 -136 136.0 val_136 -137 274.0 val_137 -138 552.0 val_138 -143 143.0 val_143 -145 145.0 val_145 -146 292.0 val_146 -149 298.0 val_149 -15 30.0 val_15 -150 150.0 val_150 -152 304.0 val_152 -153 153.0 val_153 -155 155.0 val_155 -156 156.0 val_156 -157 157.0 val_157 -158 158.0 val_158 -160 160.0 val_160 -162 162.0 val_162 -163 163.0 val_163 -164 328.0 val_164 -165 330.0 val_165 -166 166.0 val_166 -167 501.0 val_167 -168 168.0 val_168 -169 676.0 val_169 -17 17.0 val_17 -170 170.0 val_170 -172 344.0 val_172 -174 348.0 val_174 -175 350.0 val_175 -176 352.0 val_176 -177 177.0 val_177 -178 178.0 val_178 -179 358.0 val_179 -18 36.0 val_18 -180 180.0 val_180 -181 181.0 val_181 -183 183.0 val_183 -186 186.0 val_186 -187 561.0 val_187 -189 189.0 val_189 -19 19.0 val_19 -190 190.0 val_190 -191 382.0 val_191 -192 192.0 val_192 -193 579.0 val_193 -194 194.0 val_194 -195 390.0 val_195 -196 196.0 val_196 -197 394.0 val_197 -199 597.0 val_199 -2 2.0 val_2 -20 20.0 val_20 -200 400.0 val_200 -201 201.0 val_201 -202 202.0 val_202 -203 406.0 val_203 -205 410.0 val_205 -207 414.0 val_207 -208 624.0 val_208 -209 418.0 val_209 -213 426.0 val_213 -214 214.0 val_214 -216 432.0 val_216 -217 434.0 val_217 -218 218.0 val_218 -219 438.0 val_219 -221 442.0 val_221 -222 222.0 val_222 -223 446.0 val_223 -224 448.0 val_224 -226 226.0 val_226 -228 228.0 val_228 -229 458.0 val_229 -230 1150.0 val_230 -233 466.0 val_233 -235 235.0 val_235 -237 474.0 val_237 -238 476.0 val_238 -239 478.0 val_239 -24 48.0 val_24 -241 241.0 val_241 -242 484.0 val_242 -244 244.0 val_244 -247 247.0 val_247 -248 248.0 val_248 -249 249.0 val_249 -252 252.0 val_252 -255 510.0 val_255 -256 512.0 val_256 -257 257.0 val_257 -258 258.0 val_258 -26 52.0 val_26 -260 260.0 val_260 -262 262.0 val_262 -263 263.0 val_263 -265 530.0 val_265 -266 266.0 val_266 -27 27.0 val_27 -272 544.0 val_272 -273 819.0 val_273 -274 274.0 val_274 -275 275.0 val_275 -277 1108.0 val_277 -278 556.0 val_278 -28 28.0 val_28 -280 560.0 val_280 -281 562.0 val_281 -282 564.0 val_282 -283 283.0 val_283 -284 284.0 val_284 -285 285.0 val_285 -286 286.0 val_286 -287 287.0 val_287 -288 576.0 val_288 -289 289.0 val_289 -291 291.0 val_291 -292 292.0 val_292 -296 296.0 val_296 -298 894.0 val_298 -30 30.0 val_30 -302 302.0 val_302 -305 305.0 val_305 -306 306.0 val_306 -307 614.0 val_307 -308 308.0 val_308 -309 618.0 val_309 -310 310.0 val_310 -311 933.0 val_311 -315 315.0 val_315 -316 948.0 val_316 -317 634.0 val_317 -318 954.0 val_318 -321 642.0 val_321 -322 644.0 val_322 -323 323.0 val_323 -325 650.0 val_325 -327 981.0 val_327 -33 33.0 val_33 -331 662.0 val_331 -332 332.0 val_332 -333 666.0 val_333 -335 335.0 val_335 -336 336.0 val_336 -338 338.0 val_338 -339 339.0 val_339 -34 34.0 val_34 -341 341.0 val_341 -342 684.0 val_342 -344 688.0 val_344 -345 345.0 val_345 -348 1740.0 val_348 -35 105.0 val_35 -351 351.0 val_351 -353 706.0 val_353 -356 356.0 val_356 -360 360.0 val_360 -362 362.0 val_362 -364 364.0 val_364 -365 365.0 val_365 -366 366.0 val_366 -367 734.0 val_367 -368 368.0 val_368 -369 1107.0 val_369 -37 74.0 val_37 -373 373.0 val_373 -374 374.0 val_374 -375 375.0 val_375 -377 377.0 val_377 -378 378.0 val_378 -379 379.0 val_379 -382 764.0 val_382 -384 1152.0 val_384 -386 386.0 val_386 -389 389.0 val_389 -392 392.0 val_392 -393 393.0 val_393 -394 394.0 val_394 -395 790.0 val_395 -396 1188.0 val_396 -397 794.0 val_397 -399 798.0 val_399 -4 4.0 val_4 -400 400.0 val_400 -401 2005.0 val_401 -402 402.0 val_402 -403 1209.0 val_403 -404 808.0 val_404 -406 1624.0 val_406 -407 407.0 val_407 -409 1227.0 val_409 -41 41.0 val_41 -411 411.0 val_411 -413 826.0 val_413 -414 828.0 val_414 -417 1251.0 val_417 -418 418.0 val_418 -419 419.0 val_419 -42 84.0 val_42 -421 421.0 val_421 -424 848.0 val_424 -427 427.0 val_427 -429 858.0 val_429 -43 43.0 val_43 -430 1290.0 val_430 -431 1293.0 val_431 -432 432.0 val_432 -435 435.0 val_435 -436 436.0 val_436 -437 437.0 val_437 -438 1314.0 val_438 -439 878.0 val_439 -44 44.0 val_44 -443 443.0 val_443 -444 444.0 val_444 -446 446.0 val_446 -448 448.0 val_448 -449 449.0 val_449 -452 452.0 val_452 -453 453.0 val_453 -454 1362.0 val_454 -455 455.0 val_455 -457 457.0 val_457 -458 916.0 val_458 -459 918.0 val_459 -460 460.0 val_460 -462 924.0 val_462 -463 926.0 val_463 -466 1398.0 val_466 -467 467.0 val_467 -468 1872.0 val_468 -469 2345.0 val_469 -47 47.0 val_47 -470 470.0 val_470 -472 472.0 val_472 -475 475.0 val_475 -477 477.0 val_477 -478 956.0 val_478 -479 479.0 val_479 -480 1440.0 val_480 -481 481.0 val_481 -482 482.0 val_482 -483 483.0 val_483 -484 484.0 val_484 -485 485.0 val_485 -487 487.0 val_487 -489 1956.0 val_489 -490 490.0 val_490 -491 491.0 val_491 -492 984.0 val_492 -493 493.0 val_493 -494 494.0 val_494 -495 495.0 val_495 -496 496.0 val_496 -497 497.0 val_497 -498 1494.0 val_498 -5 15.0 val_5 -51 102.0 val_51 -53 53.0 val_53 -54 54.0 val_54 -57 57.0 val_57 -58 116.0 val_58 -64 64.0 val_64 -65 65.0 val_65 -66 66.0 val_66 -67 134.0 val_67 -69 69.0 val_69 -70 210.0 val_70 -72 144.0 val_72 -74 74.0 val_74 -76 152.0 val_76 -77 77.0 val_77 -78 78.0 val_78 -8 8.0 val_8 -80 80.0 val_80 -82 82.0 val_82 -83 166.0 val_83 -84 168.0 val_84 -85 85.0 val_85 -86 86.0 val_86 -87 87.0 val_87 -9 9.0 val_9 -90 270.0 val_90 -92 92.0 val_92 -95 190.0 val_95 -96 96.0 val_96 -97 194.0 val_97 -98 196.0 val_98 -PREHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n2 -PREHOOK: Output: default@e2_n3 -POSTHOOK: query: FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n2 -POSTHOOK: Output: default@e2_n3 -POSTHOOK: Lineage: e1_n2.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e1_n2.keyd EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n3.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n3.keyd EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from e1_n2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e1_n2 -#### A masked pattern was here #### -POSTHOOK: query: select * from e1_n2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e1_n2 -#### A masked pattern was here #### -0 1.0 -10 1.0 -100 1.0 -103 1.0 -104 1.0 -105 1.0 -11 1.0 -111 1.0 -113 1.0 -114 1.0 -116 1.0 -118 1.0 -119 1.0 -12 1.0 -120 1.0 -125 1.0 -126 1.0 -128 1.0 -129 1.0 -131 1.0 -133 1.0 -134 1.0 -136 1.0 -137 1.0 -138 1.0 -143 1.0 -145 1.0 -146 1.0 -149 1.0 -15 1.0 -150 1.0 -152 1.0 -153 1.0 -155 1.0 -156 1.0 -157 1.0 -158 1.0 -160 1.0 -162 1.0 -163 1.0 -164 1.0 -165 1.0 -166 1.0 -167 1.0 -168 1.0 -169 1.0 -17 1.0 -170 1.0 -172 1.0 -174 1.0 -175 1.0 -176 1.0 -177 1.0 -178 1.0 -179 1.0 -18 1.0 -180 1.0 -181 1.0 -183 1.0 -186 1.0 -187 1.0 -189 1.0 -19 1.0 -190 1.0 -191 1.0 -192 1.0 -193 1.0 -194 1.0 -195 1.0 -196 1.0 -197 1.0 -199 1.0 -2 1.0 -20 1.0 -200 1.0 -201 1.0 -202 1.0 -203 1.0 -205 1.0 -207 1.0 -208 1.0 -209 1.0 -213 1.0 -214 1.0 -216 1.0 -217 1.0 -218 1.0 -219 1.0 -221 1.0 -222 1.0 -223 1.0 -224 1.0 -226 1.0 -228 1.0 -229 1.0 -230 1.0 -233 1.0 -235 1.0 -237 1.0 -238 1.0 -239 1.0 -24 1.0 -241 1.0 -242 1.0 -244 1.0 -247 1.0 -248 1.0 -249 1.0 -252 1.0 -255 1.0 -256 1.0 -257 1.0 -258 1.0 -26 1.0 -260 1.0 -262 1.0 -263 1.0 -265 1.0 -266 1.0 -27 1.0 -272 1.0 -273 1.0 -274 1.0 -275 1.0 -277 1.0 -278 1.0 -28 1.0 -280 1.0 -281 1.0 -282 1.0 -283 1.0 -284 1.0 -285 1.0 -286 1.0 -287 1.0 -288 1.0 -289 1.0 -291 1.0 -292 1.0 -296 1.0 -298 1.0 -30 1.0 -302 1.0 -305 1.0 -306 1.0 -307 1.0 -308 1.0 -309 1.0 -310 1.0 -311 1.0 -315 1.0 -316 1.0 -317 1.0 -318 1.0 -321 1.0 -322 1.0 -323 1.0 -325 1.0 -327 1.0 -33 1.0 -331 1.0 -332 1.0 -333 1.0 -335 1.0 -336 1.0 -338 1.0 -339 1.0 -34 1.0 -341 1.0 -342 1.0 -344 1.0 -345 1.0 -348 1.0 -35 1.0 -351 1.0 -353 1.0 -356 1.0 -360 1.0 -362 1.0 -364 1.0 -365 1.0 -366 1.0 -367 1.0 -368 1.0 -369 1.0 -37 1.0 -373 1.0 -374 1.0 -375 1.0 -377 1.0 -378 1.0 -379 1.0 -382 1.0 -384 1.0 -386 1.0 -389 1.0 -392 1.0 -393 1.0 -394 1.0 -395 1.0 -396 1.0 -397 1.0 -399 1.0 -4 1.0 -400 1.0 -401 1.0 -402 1.0 -403 1.0 -404 1.0 -406 1.0 -407 1.0 -409 1.0 -41 1.0 -411 1.0 -413 1.0 -414 1.0 -417 1.0 -418 1.0 -419 1.0 -42 1.0 -421 1.0 -424 1.0 -427 1.0 -429 1.0 -43 1.0 -430 1.0 -431 1.0 -432 1.0 -435 1.0 -436 1.0 -437 1.0 -438 1.0 -439 1.0 -44 1.0 -443 1.0 -444 1.0 -446 1.0 -448 1.0 -449 1.0 -452 1.0 -453 1.0 -454 1.0 -455 1.0 -457 1.0 -458 1.0 -459 1.0 -460 1.0 -462 1.0 -463 1.0 -466 1.0 -467 1.0 -468 1.0 -469 1.0 -47 1.0 -470 1.0 -472 1.0 -475 1.0 -477 1.0 -478 1.0 -479 1.0 -480 1.0 -481 1.0 -482 1.0 -483 1.0 -484 1.0 -485 1.0 -487 1.0 -489 1.0 -490 1.0 -491 1.0 -492 1.0 -493 1.0 -494 1.0 -495 1.0 -496 1.0 -497 1.0 -498 1.0 -5 1.0 -51 1.0 -53 1.0 -54 1.0 -57 1.0 -58 1.0 -64 1.0 -65 1.0 -66 1.0 -67 1.0 -69 1.0 -70 1.0 -72 1.0 -74 1.0 -76 1.0 -77 1.0 -78 1.0 -8 1.0 -80 1.0 -82 1.0 -83 1.0 -84 1.0 -85 1.0 -86 1.0 -87 1.0 -9 1.0 -90 1.0 -92 1.0 -95 1.0 -96 1.0 -97 1.0 -98 1.0 -PREHOOK: query: select * from e2_n3 -PREHOOK: type: QUERY -PREHOOK: Input: default@e2_n3 -#### A masked pattern was here #### -POSTHOOK: query: select * from e2_n3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e2_n3 -#### A masked pattern was here #### -0 0.0 val_0 -10 10.0 val_10 -100 200.0 val_100 -103 206.0 val_103 -104 208.0 val_104 -105 105.0 val_105 -11 11.0 val_11 -111 111.0 val_111 -113 226.0 val_113 -114 114.0 val_114 -116 116.0 val_116 -118 236.0 val_118 -119 357.0 val_119 -12 24.0 val_12 -120 240.0 val_120 -125 250.0 val_125 -126 126.0 val_126 -128 384.0 val_128 -129 258.0 val_129 -131 131.0 val_131 -133 133.0 val_133 -134 268.0 val_134 -136 136.0 val_136 -137 274.0 val_137 -138 552.0 val_138 -143 143.0 val_143 -145 145.0 val_145 -146 292.0 val_146 -149 298.0 val_149 -15 30.0 val_15 -150 150.0 val_150 -152 304.0 val_152 -153 153.0 val_153 -155 155.0 val_155 -156 156.0 val_156 -157 157.0 val_157 -158 158.0 val_158 -160 160.0 val_160 -162 162.0 val_162 -163 163.0 val_163 -164 328.0 val_164 -165 330.0 val_165 -166 166.0 val_166 -167 501.0 val_167 -168 168.0 val_168 -169 676.0 val_169 -17 17.0 val_17 -170 170.0 val_170 -172 344.0 val_172 -174 348.0 val_174 -175 350.0 val_175 -176 352.0 val_176 -177 177.0 val_177 -178 178.0 val_178 -179 358.0 val_179 -18 36.0 val_18 -180 180.0 val_180 -181 181.0 val_181 -183 183.0 val_183 -186 186.0 val_186 -187 561.0 val_187 -189 189.0 val_189 -19 19.0 val_19 -190 190.0 val_190 -191 382.0 val_191 -192 192.0 val_192 -193 579.0 val_193 -194 194.0 val_194 -195 390.0 val_195 -196 196.0 val_196 -197 394.0 val_197 -199 597.0 val_199 -2 2.0 val_2 -20 20.0 val_20 -200 400.0 val_200 -201 201.0 val_201 -202 202.0 val_202 -203 406.0 val_203 -205 410.0 val_205 -207 414.0 val_207 -208 624.0 val_208 -209 418.0 val_209 -213 426.0 val_213 -214 214.0 val_214 -216 432.0 val_216 -217 434.0 val_217 -218 218.0 val_218 -219 438.0 val_219 -221 442.0 val_221 -222 222.0 val_222 -223 446.0 val_223 -224 448.0 val_224 -226 226.0 val_226 -228 228.0 val_228 -229 458.0 val_229 -230 1150.0 val_230 -233 466.0 val_233 -235 235.0 val_235 -237 474.0 val_237 -238 476.0 val_238 -239 478.0 val_239 -24 48.0 val_24 -241 241.0 val_241 -242 484.0 val_242 -244 244.0 val_244 -247 247.0 val_247 -248 248.0 val_248 -249 249.0 val_249 -252 252.0 val_252 -255 510.0 val_255 -256 512.0 val_256 -257 257.0 val_257 -258 258.0 val_258 -26 52.0 val_26 -260 260.0 val_260 -262 262.0 val_262 -263 263.0 val_263 -265 530.0 val_265 -266 266.0 val_266 -27 27.0 val_27 -272 544.0 val_272 -273 819.0 val_273 -274 274.0 val_274 -275 275.0 val_275 -277 1108.0 val_277 -278 556.0 val_278 -28 28.0 val_28 -280 560.0 val_280 -281 562.0 val_281 -282 564.0 val_282 -283 283.0 val_283 -284 284.0 val_284 -285 285.0 val_285 -286 286.0 val_286 -287 287.0 val_287 -288 576.0 val_288 -289 289.0 val_289 -291 291.0 val_291 -292 292.0 val_292 -296 296.0 val_296 -298 894.0 val_298 -30 30.0 val_30 -302 302.0 val_302 -305 305.0 val_305 -306 306.0 val_306 -307 614.0 val_307 -308 308.0 val_308 -309 618.0 val_309 -310 310.0 val_310 -311 933.0 val_311 -315 315.0 val_315 -316 948.0 val_316 -317 634.0 val_317 -318 954.0 val_318 -321 642.0 val_321 -322 644.0 val_322 -323 323.0 val_323 -325 650.0 val_325 -327 981.0 val_327 -33 33.0 val_33 -331 662.0 val_331 -332 332.0 val_332 -333 666.0 val_333 -335 335.0 val_335 -336 336.0 val_336 -338 338.0 val_338 -339 339.0 val_339 -34 34.0 val_34 -341 341.0 val_341 -342 684.0 val_342 -344 688.0 val_344 -345 345.0 val_345 -348 1740.0 val_348 -35 105.0 val_35 -351 351.0 val_351 -353 706.0 val_353 -356 356.0 val_356 -360 360.0 val_360 -362 362.0 val_362 -364 364.0 val_364 -365 365.0 val_365 -366 366.0 val_366 -367 734.0 val_367 -368 368.0 val_368 -369 1107.0 val_369 -37 74.0 val_37 -373 373.0 val_373 -374 374.0 val_374 -375 375.0 val_375 -377 377.0 val_377 -378 378.0 val_378 -379 379.0 val_379 -382 764.0 val_382 -384 1152.0 val_384 -386 386.0 val_386 -389 389.0 val_389 -392 392.0 val_392 -393 393.0 val_393 -394 394.0 val_394 -395 790.0 val_395 -396 1188.0 val_396 -397 794.0 val_397 -399 798.0 val_399 -4 4.0 val_4 -400 400.0 val_400 -401 2005.0 val_401 -402 402.0 val_402 -403 1209.0 val_403 -404 808.0 val_404 -406 1624.0 val_406 -407 407.0 val_407 -409 1227.0 val_409 -41 41.0 val_41 -411 411.0 val_411 -413 826.0 val_413 -414 828.0 val_414 -417 1251.0 val_417 -418 418.0 val_418 -419 419.0 val_419 -42 84.0 val_42 -421 421.0 val_421 -424 848.0 val_424 -427 427.0 val_427 -429 858.0 val_429 -43 43.0 val_43 -430 1290.0 val_430 -431 1293.0 val_431 -432 432.0 val_432 -435 435.0 val_435 -436 436.0 val_436 -437 437.0 val_437 -438 1314.0 val_438 -439 878.0 val_439 -44 44.0 val_44 -443 443.0 val_443 -444 444.0 val_444 -446 446.0 val_446 -448 448.0 val_448 -449 449.0 val_449 -452 452.0 val_452 -453 453.0 val_453 -454 1362.0 val_454 -455 455.0 val_455 -457 457.0 val_457 -458 916.0 val_458 -459 918.0 val_459 -460 460.0 val_460 -462 924.0 val_462 -463 926.0 val_463 -466 1398.0 val_466 -467 467.0 val_467 -468 1872.0 val_468 -469 2345.0 val_469 -47 47.0 val_47 -470 470.0 val_470 -472 472.0 val_472 -475 475.0 val_475 -477 477.0 val_477 -478 956.0 val_478 -479 479.0 val_479 -480 1440.0 val_480 -481 481.0 val_481 -482 482.0 val_482 -483 483.0 val_483 -484 484.0 val_484 -485 485.0 val_485 -487 487.0 val_487 -489 1956.0 val_489 -490 490.0 val_490 -491 491.0 val_491 -492 984.0 val_492 -493 493.0 val_493 -494 494.0 val_494 -495 495.0 val_495 -496 496.0 val_496 -497 497.0 val_497 -498 1494.0 val_498 -5 15.0 val_5 -51 102.0 val_51 -53 53.0 val_53 -54 54.0 val_54 -57 57.0 val_57 -58 116.0 val_58 -64 64.0 val_64 -65 65.0 val_65 -66 66.0 val_66 -67 134.0 val_67 -69 69.0 val_69 -70 210.0 val_70 -72 144.0 val_72 -74 74.0 val_74 -76 152.0 val_76 -77 77.0 val_77 -78 78.0 val_78 -8 8.0 val_8 -80 80.0 val_80 -82 82.0 val_82 -83 166.0 val_83 -84 168.0 val_84 -85 85.0 val_85 -86 86.0 val_86 -87 87.0 val_87 -9 9.0 val_9 -90 270.0 val_90 -92 92.0 val_92 -95 190.0 val_95 -96 96.0 val_96 -97 194.0 val_97 -98 196.0 val_98 -PREHOOK: query: explain -from src -insert overwrite table e1_n2 -select key, count(distinct value) group by key -insert overwrite table e3 -select value, count(distinct key) group by value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n2 -PREHOOK: Output: default@e3 -POSTHOOK: query: explain -from src -insert overwrite table e1_n2 -select key, count(distinct value) group by key -insert overwrite table e3 -select value, count(distinct key) group by value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n2 -POSTHOOK: Output: default@e3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-7 - Stage-4 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-1, Stage-4, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-5 - Stage-7 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT value) - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT key) - keys: value (type: string), key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd - Column Types: string, double - Table: default.e1_n2 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd - Column Types: string, double - Table: default.e3 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e3 - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e3 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -INSERT overwrite table e3 - SELECT key, COUNT(distinct keyD) group by key, keyD, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n2 -PREHOOK: Output: default@e2_n3 -PREHOOK: Output: default@e3 -POSTHOOK: query: explain -FROM (select key, cast(key as double) as keyD, value from src order by key) a -INSERT OVERWRITE TABLE e1_n2 - SELECT key, COUNT(distinct value) group by key -INSERT OVERWRITE TABLE e2_n3 - SELECT key, sum(keyD), value group by key, value -INSERT overwrite table e3 - SELECT key, COUNT(distinct keyD) group by key, keyD, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n2 -POSTHOOK: Output: default@e2_n3 -POSTHOOK: Output: default@e3 -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-0 depends on stages: Stage-3 - Stage-4 depends on stages: Stage-0, Stage-5, Stage-8, Stage-11 - Stage-5 depends on stages: Stage-3 - Stage-7 depends on stages: Stage-1, Stage-5, Stage-8, Stage-11 - Stage-10 depends on stages: Stage-2, Stage-5, Stage-8, Stage-11 - Stage-6 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-6 - Stage-8 depends on stages: Stage-6 - Stage-9 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-9 - Stage-11 depends on stages: Stage-9 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), UDFToDouble(key) (type: double), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT _col2) - keys: _col0 (type: string), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col1) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: key, keyd - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n2 - - Stage: Stage-4 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd - Column Types: string, double - Table: default.e1_n2 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd, value - Column Types: string, double, string - Table: default.e2_n3 - - Stage: Stage-10 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, keyd - Column Types: string, double - Table: default.e3 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n3 - Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) - outputColumnNames: key, keyd, value - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n3 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: string) - null sort order: zzzz - sort order: ++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: string) - Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col3:0._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToDouble(_col3) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e3 - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: key, keyd - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(keyd, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e3 - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - diff --git ql/src/test/results/clientpositive/multi_insert_gby4.q.out ql/src/test/results/clientpositive/multi_insert_gby4.q.out deleted file mode 100644 index abb749b78b..0000000000 --- ql/src/test/results/clientpositive/multi_insert_gby4.q.out +++ /dev/null @@ -1,423 +0,0 @@ -PREHOOK: query: create table e1_n4 (key string, count int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e1_n4 -POSTHOOK: query: create table e1_n4 (key string, count int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e1_n4 -PREHOOK: query: create table e2_n5 (key string, count int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e2_n5 -POSTHOOK: query: create table e2_n5 (key string, count int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e2_n5 -PREHOOK: query: create table e3_n0 (key string, count int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e3_n0 -POSTHOOK: query: create table e3_n0 (key string, count int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e3_n0 -PREHOOK: query: explain -FROM (SELECT key, value FROM src) a -INSERT OVERWRITE TABLE e1_n4 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n5 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -INSERT OVERWRITE TABLE e3_n0 - SELECT key, COUNT(*) WHERE key>490 GROUP BY key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n4 -PREHOOK: Output: default@e2_n5 -PREHOOK: Output: default@e3_n0 -POSTHOOK: query: explain -FROM (SELECT key, value FROM src) a -INSERT OVERWRITE TABLE e1_n4 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n5 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -INSERT OVERWRITE TABLE e3_n0 - SELECT key, COUNT(*) WHERE key>490 GROUP BY key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n4 -POSTHOOK: Output: default@e2_n5 -POSTHOOK: Output: default@e3_n0 -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-0 depends on stages: Stage-3 - Stage-4 depends on stages: Stage-0, Stage-5, Stage-7, Stage-9 - Stage-5 depends on stages: Stage-3 - Stage-6 depends on stages: Stage-1, Stage-5, Stage-7, Stage-9 - Stage-8 depends on stages: Stage-2, Stage-5, Stage-7, Stage-9 - Stage-1 depends on stages: Stage-3 - Stage-7 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-3 - Stage-9 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col0 > 490) or ((_col0 > 500) or (_col0 > 450))) (type: boolean) - Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 498 Data size: 43326 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 > 450) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: key, count - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (KEY._col0 > 500) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: key, count - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (KEY._col0 > 490) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 106 Data size: 10070 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e3_n0 - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: key, count - Statistics: Num rows: 106 Data size: 9646 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(count, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e1_n4 - - Stage: Stage-4 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, count - Column Types: string, int - Table: default.e1_n4 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, count - Column Types: string, int - Table: default.e2_n5 - - Stage: Stage-8 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, count - Column Types: string, int - Table: default.e3_n0 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e2_n5 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.e3_n0 - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: FROM (SELECT key, value FROM src) a -INSERT OVERWRITE TABLE e1_n4 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n5 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -INSERT OVERWRITE TABLE e3_n0 - SELECT key, COUNT(*) WHERE key>490 GROUP BY key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@e1_n4 -PREHOOK: Output: default@e2_n5 -PREHOOK: Output: default@e3_n0 -POSTHOOK: query: FROM (SELECT key, value FROM src) a -INSERT OVERWRITE TABLE e1_n4 - SELECT key, COUNT(*) WHERE key>450 GROUP BY key -INSERT OVERWRITE TABLE e2_n5 - SELECT key, COUNT(*) WHERE key>500 GROUP BY key -INSERT OVERWRITE TABLE e3_n0 - SELECT key, COUNT(*) WHERE key>490 GROUP BY key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@e1_n4 -POSTHOOK: Output: default@e2_n5 -POSTHOOK: Output: default@e3_n0 -POSTHOOK: Lineage: e1_n4.count EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: e1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e2_n5.count EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: e2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: e3_n0.count EXPRESSION [(src)src.null, ] -POSTHOOK: Lineage: e3_n0.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -PREHOOK: query: select * from e1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@e1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from e1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e1_n4 -#### A masked pattern was here #### -452 1 -453 1 -454 3 -455 1 -457 1 -458 2 -459 2 -460 1 -462 2 -463 2 -466 3 -467 1 -468 4 -469 5 -470 1 -472 1 -475 1 -477 1 -478 2 -479 1 -480 3 -481 1 -482 1 -483 1 -484 1 -485 1 -487 1 -489 4 -490 1 -491 1 -492 2 -493 1 -494 1 -495 1 -496 1 -497 1 -498 3 -PREHOOK: query: select * from e2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@e2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from e2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e2_n5 -#### A masked pattern was here #### -PREHOOK: query: select * from e3_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@e3_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * from e3_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e3_n0 -#### A masked pattern was here #### -491 1 -492 2 -493 1 -494 1 -495 1 -496 1 -497 1 -498 3 diff --git ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out deleted file mode 100644 index 4e34c11af0..0000000000 --- ql/src/test/results/clientpositive/multi_insert_move_tasks_share_dependencies.q.out +++ /dev/null @@ -1,6009 +0,0 @@ -PREHOOK: query: create table src_multi1_n4 like src -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_multi1_n4 -POSTHOOK: query: create table src_multi1_n4 like src -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_multi1_n4 -PREHOOK: query: create table src_multi2_n5 like src -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: create table src_multi2_n5 like src -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_multi2_n5 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-4 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-6 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1, Stage-6 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-9 depends on stages: Stage-2 , consists of Stage-6, Stage-5, Stage-7 - Stage-6 - Stage-4 depends on stages: Stage-6, Stage-5, Stage-8, Stage-2 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-11 - Stage-1 depends on stages: Stage-4 - Stage-10 depends on stages: Stage-1, Stage-11 - Stage-5 - Stage-7 - Stage-8 depends on stages: Stage-7 - Stage-11 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-9 - Conditional Operator - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-10 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-4 depends on stages: Stage-2, Stage-7, Stage-6, Stage-9 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-11 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1, Stage-11 - Stage-10 depends on stages: Stage-2 , consists of Stage-7, Stage-6, Stage-8 - Stage-7 - Stage-6 - Stage-8 - Stage-9 depends on stages: Stage-8 - Stage-11 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-10 - Conditional Operator - - Stage: Stage-7 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-9 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-9 depends on stages: Stage-2 , consists of Stage-6, Stage-5, Stage-7 - Stage-6 - Stage-4 depends on stages: Stage-6, Stage-5, Stage-8, Stage-12, Stage-11, Stage-14 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-16 - Stage-1 depends on stages: Stage-4 - Stage-10 depends on stages: Stage-1, Stage-16 - Stage-5 - Stage-7 - Stage-8 depends on stages: Stage-7 - Stage-15 depends on stages: Stage-2 , consists of Stage-12, Stage-11, Stage-13 - Stage-12 - Stage-11 - Stage-13 - Stage-14 depends on stages: Stage-13 - Stage-16 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-9 - Conditional Operator - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-10 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-15 - Conditional Operator - - Stage: Stage-12 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-13 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-14 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-16 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-4 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-5, Stage-7 - Stage-1 depends on stages: Stage-4 - Stage-6 depends on stages: Stage-1, Stage-5, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-7 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -2 val_2 -4 val_4 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -15 val_15 -17 val_17 -18 val_18 -19 val_19 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-9 depends on stages: Stage-2 , consists of Stage-6, Stage-5, Stage-7 - Stage-6 - Stage-4 depends on stages: Stage-6, Stage-5, Stage-8, Stage-13, Stage-12, Stage-15 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-10, Stage-17 - Stage-1 depends on stages: Stage-4 - Stage-11 depends on stages: Stage-1, Stage-10, Stage-17 - Stage-5 - Stage-7 - Stage-8 depends on stages: Stage-7 - Stage-10 depends on stages: Stage-2 - Stage-16 depends on stages: Stage-2 , consists of Stage-13, Stage-12, Stage-14 - Stage-13 - Stage-12 - Stage-14 - Stage-15 depends on stages: Stage-14 - Stage-17 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-9 - Conditional Operator - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-11 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-16 - Conditional Operator - - Stage: Stage-13 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-12 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-14 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-15 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-17 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -2 val_2 -4 val_4 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -15 val_15 -17 val_17 -18 val_18 -19 val_19 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-4 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-5, Stage-7 - Stage-1 depends on stages: Stage-4 - Stage-6 depends on stages: Stage-1, Stage-5, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-7 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -2 val_2 -4 val_4 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -15 val_15 -17 val_17 -18 val_18 -19 val_19 -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-9 depends on stages: Stage-2 , consists of Stage-6, Stage-5, Stage-7 - Stage-6 - Stage-4 depends on stages: Stage-6, Stage-5, Stage-8, Stage-13, Stage-12, Stage-15 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-10, Stage-17 - Stage-1 depends on stages: Stage-4 - Stage-11 depends on stages: Stage-1, Stage-10, Stage-17 - Stage-5 - Stage-7 - Stage-8 depends on stages: Stage-7 - Stage-10 depends on stages: Stage-2 - Stage-16 depends on stages: Stage-2 , consists of Stage-13, Stage-12, Stage-14 - Stage-13 - Stage-12 - Stage-14 - Stage-15 depends on stages: Stage-14 - Stage-17 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-9 - Conditional Operator - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-11 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-16 - Conditional Operator - - Stage: Stage-13 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-12 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-14 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-15 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-17 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 group by key, value -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -2 val_2 -4 val_4 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -15 val_15 -17 val_17 -18 val_18 -19 val_19 -PREHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-4 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-6 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1, Stage-6 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -2 val_2 -2 val_2 -4 val_4 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -8 val_8 -9 val_9 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -11 val_11 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -17 val_17 -17 val_17 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -19 val_19 -19 val_19 -PREHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-9 depends on stages: Stage-2 , consists of Stage-6, Stage-5, Stage-7 - Stage-6 - Stage-4 depends on stages: Stage-6, Stage-5, Stage-8, Stage-2 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-11 - Stage-1 depends on stages: Stage-4 - Stage-10 depends on stages: Stage-1, Stage-11 - Stage-5 - Stage-7 - Stage-8 depends on stages: Stage-7 - Stage-11 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-9 - Conditional Operator - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-10 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -2 val_2 -2 val_2 -4 val_4 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -8 val_8 -9 val_9 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -11 val_11 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -17 val_17 -17 val_17 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -19 val_19 -19 val_19 -PREHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-4 depends on stages: Stage-2, Stage-7, Stage-6, Stage-9 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-11 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1, Stage-11 - Stage-10 depends on stages: Stage-2 , consists of Stage-7, Stage-6, Stage-8 - Stage-7 - Stage-6 - Stage-8 - Stage-9 depends on stages: Stage-8 - Stage-11 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-10 - Conditional Operator - - Stage: Stage-7 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-9 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -2 val_2 -2 val_2 -4 val_4 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -8 val_8 -9 val_9 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -11 val_11 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -17 val_17 -17 val_17 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -19 val_19 -19 val_19 -PREHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-9 depends on stages: Stage-2 , consists of Stage-6, Stage-5, Stage-7 - Stage-6 - Stage-4 depends on stages: Stage-6, Stage-5, Stage-8, Stage-12, Stage-11, Stage-14 - Stage-0 depends on stages: Stage-4 - Stage-3 depends on stages: Stage-0, Stage-16 - Stage-1 depends on stages: Stage-4 - Stage-10 depends on stages: Stage-1, Stage-16 - Stage-5 - Stage-7 - Stage-8 depends on stages: Stage-7 - Stage-15 depends on stages: Stage-2 , consists of Stage-12, Stage-11, Stage-13 - Stage-12 - Stage-11 - Stage-13 - Stage-14 depends on stages: Stage-13 - Stage-16 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 < 10) (type: boolean) - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 333 Data size: 59274 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((_col0 > 10) and (_col0 < 20)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-9 - Conditional Operator - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-10 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-15 - Conditional Operator - - Stage: Stage-12 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-13 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-14 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-16 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from (select * from src union all select * from src) s -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -2 val_2 -2 val_2 -4 val_4 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -8 val_8 -9 val_9 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -11 val_11 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -17 val_17 -17 val_17 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -19 val_19 -19 val_19 -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 0) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 2) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 4) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 3 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 0) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 2) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 4) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 3 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 0) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 2) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 4) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 3 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 0) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 2) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: (key = 4) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-4 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 3 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2, Stage-4 - Stage-0 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 2 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2, Stage-4 - Stage-0 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 2 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2, Stage-4 - Stage-0 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 2 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2, Stage-4 - Stage-0 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Dependency Collection - - Stage: Stage-0 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: from src -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -Found 2 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-6 depends on stages: Stage-4, Stage-9, Stage-10 - Stage-0 depends on stages: Stage-6 - Stage-5 depends on stages: Stage-0, Stage-8, Stage-2, Stage-3 - Stage-1 depends on stages: Stage-6 - Stage-7 depends on stages: Stage-1, Stage-8, Stage-2, Stage-3 - Stage-8 depends on stages: Stage-4 - Stage-9 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-9 - Stage-10 depends on stages: Stage-9 - Stage-3 depends on stages: Stage-10 - -STAGE PLANS: - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-7 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -Found 2 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-6 depends on stages: Stage-4, Stage-9, Stage-8, Stage-11, Stage-14, Stage-15 - Stage-0 depends on stages: Stage-6 - Stage-5 depends on stages: Stage-0, Stage-13, Stage-2, Stage-3 - Stage-1 depends on stages: Stage-6 - Stage-7 depends on stages: Stage-1, Stage-13, Stage-2, Stage-3 - Stage-12 depends on stages: Stage-4 , consists of Stage-9, Stage-8, Stage-10 - Stage-9 - Stage-8 - Stage-10 - Stage-11 depends on stages: Stage-10 - Stage-13 depends on stages: Stage-4 - Stage-14 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-14 - Stage-15 depends on stages: Stage-14 - Stage-3 depends on stages: Stage-15 - -STAGE PLANS: - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-7 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-12 - Conditional Operator - - Stage: Stage-9 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-11 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-13 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-14 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-15 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -Found 2 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-11 depends on stages: Stage-4 , consists of Stage-8, Stage-7, Stage-9 - Stage-8 - Stage-6 depends on stages: Stage-8, Stage-7, Stage-10, Stage-4, Stage-14, Stage-15 - Stage-0 depends on stages: Stage-6 - Stage-5 depends on stages: Stage-0, Stage-13, Stage-2, Stage-3 - Stage-1 depends on stages: Stage-6 - Stage-12 depends on stages: Stage-1, Stage-13, Stage-2, Stage-3 - Stage-7 - Stage-9 - Stage-10 depends on stages: Stage-9 - Stage-13 depends on stages: Stage-4 - Stage-14 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-14 - Stage-15 depends on stages: Stage-14 - Stage-3 depends on stages: Stage-15 - -STAGE PLANS: - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-11 - Conditional Operator - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-6 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-12 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-10 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-13 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-14 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-15 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -Found 2 items -#### A masked pattern was here #### -PREHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: explain -from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-11 depends on stages: Stage-4 , consists of Stage-8, Stage-7, Stage-9 - Stage-8 - Stage-6 depends on stages: Stage-8, Stage-7, Stage-10, Stage-14, Stage-13, Stage-16, Stage-19, Stage-20 - Stage-0 depends on stages: Stage-6 - Stage-5 depends on stages: Stage-0, Stage-18, Stage-2, Stage-3 - Stage-1 depends on stages: Stage-6 - Stage-12 depends on stages: Stage-1, Stage-18, Stage-2, Stage-3 - Stage-7 - Stage-9 - Stage-10 depends on stages: Stage-9 - Stage-17 depends on stages: Stage-4 , consists of Stage-14, Stage-13, Stage-15 - Stage-14 - Stage-13 - Stage-15 - Stage-16 depends on stages: Stage-15 - Stage-18 depends on stages: Stage-4 - Stage-19 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-19 - Stage-20 depends on stages: Stage-19 - Stage-3 depends on stages: Stage-20 - -STAGE PLANS: - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key < 10) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Filter Operator - predicate: ((key > 10) and (key < 20)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (((key > 10) and (key < 20)) or (key < 10)) (type: boolean) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-11 - Conditional Operator - - Stage: Stage-8 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-6 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi1_n4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-12 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_multi2_n5 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi1_n4 - - Stage: Stage-10 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-17 - Conditional Operator - - Stage: Stage-14 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-13 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-15 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_multi2_n5 - - Stage: Stage-16 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-18 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-19 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 221 Data size: 39338 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (KEY._col0 < 10) (type: boolean) - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 73 Data size: 12994 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Filter Operator - predicate: ((KEY._col0 > 10) and (KEY._col0 < 20)) (type: boolean) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - - Stage: Stage-20 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 24 Data size: 4272 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Move Operator - files: - hdfs directory: false -#### A masked pattern was here #### - -PREHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: Output: default@src_multi1_n4 -PREHOOK: Output: default@src_multi2_n5 -POSTHOOK: query: from src -insert overwrite table src_multi1_n4 select * where key < 10 -insert overwrite table src_multi2_n5 select * where key > 10 and key < 20 -#### A masked pattern was here #### -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: Output: default@src_multi1_n4 -POSTHOOK: Output: default@src_multi2_n5 -POSTHOOK: Lineage: src_multi1_n4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi1_n4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_multi2_n5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_multi1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi1_n4 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -9 val_9 -PREHOOK: query: select * from src_multi2_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_multi2_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_multi2_n5 -#### A masked pattern was here #### -11 val_11 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -17 val_17 -18 val_18 -18 val_18 -19 val_19 -Found 2 items -#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/multi_insert_with_join2.q.out ql/src/test/results/clientpositive/multi_insert_with_join2.q.out deleted file mode 100644 index bdb876e618..0000000000 --- ql/src/test/results/clientpositive/multi_insert_with_join2.q.out +++ /dev/null @@ -1,1678 +0,0 @@ -PREHOOK: query: CREATE TABLE T_A ( id STRING, val STRING ) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T_A -POSTHOOK: query: CREATE TABLE T_A ( id STRING, val STRING ) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T_A -PREHOOK: query: CREATE TABLE T_B ( id STRING, val STRING ) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T_B -POSTHOOK: query: CREATE TABLE T_B ( id STRING, val STRING ) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T_B -PREHOOK: query: CREATE TABLE join_result_1 ( ida STRING, vala STRING, idb STRING, valb STRING ) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@join_result_1 -POSTHOOK: query: CREATE TABLE join_result_1 ( ida STRING, vala STRING, idb STRING, valb STRING ) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@join_result_1 -PREHOOK: query: CREATE TABLE join_result_3 ( ida STRING, vala STRING, idb STRING, valb STRING ) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: CREATE TABLE join_result_3 ( ida STRING, vala STRING, idb STRING, valb STRING ) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@join_result_3 -PREHOOK: query: INSERT INTO TABLE T_A -VALUES ('Id_1', 'val_101'), ('Id_2', 'val_102'), ('Id_3', 'val_103') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t_a -POSTHOOK: query: INSERT INTO TABLE T_A -VALUES ('Id_1', 'val_101'), ('Id_2', 'val_102'), ('Id_3', 'val_103') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t_a -POSTHOOK: Lineage: t_a.id SCRIPT [] -POSTHOOK: Lineage: t_a.val SCRIPT [] -PREHOOK: query: INSERT INTO TABLE T_B -VALUES ('Id_1', 'val_103'), ('Id_2', 'val_104') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t_b -POSTHOOK: query: INSERT INTO TABLE T_B -VALUES ('Id_1', 'val_103'), ('Id_2', 'val_104') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t_b -POSTHOOK: Lineage: t_b.id SCRIPT [] -POSTHOOK: Lineage: t_b.val SCRIPT [] -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_1 -POSTHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_1 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: (id = 'Id_1') (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (id = 'Id_1') (type: boolean) - Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: val (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - alias: b - filterExpr: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'Id_1' (type: string), _col0 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_1 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_3 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: val (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - alias: b - filterExpr: ((id = 'Id_2') and (val = 'val_104')) (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((id = 'Id_2') and (val = 'val_104')) (type: boolean) - Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'Id_2' (type: string), _col0 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_3 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_1 -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_1 -POSTHOOK: Output: default@join_result_3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-0 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - TableScan - alias: b - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 id (type: string) - 1 id (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2') and (_col1 <> _col6)) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_3 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_1 - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_1 -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: explain -FROM T_A a LEFT JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_1 -POSTHOOK: Output: default@join_result_3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - TableScan - alias: b - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 id (type: string) - 1 id (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_1 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_3 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_1 -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.*, b.* -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.*, b.* -WHERE b.val = 'val_104' AND b.id = 'Id_2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_1 -POSTHOOK: Output: default@join_result_3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - TableScan - alias: b - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 id (type: string) - 1 id (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_1 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_3 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT * -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT * -WHERE b.val = 'val_104' AND b.id = 'Id_2' -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_1 -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT * -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT * -WHERE b.val = 'val_104' AND b.id = 'Id_2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_1 -POSTHOOK: Output: default@join_result_3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - TableScan - alias: b - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: id (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: id (type: string) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: val (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 id (type: string) - 1 id (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col5 = 'Id_1') and (_col6 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col6 = 'val_104') and (_col5 = 'Id_2')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_1 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_3 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.id, a.val, b.id, b.val -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.id, a.val, b.id, b.val -WHERE b.val = 'val_104' AND b.id = 'Id_2' -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_1 -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.id, a.val, b.id, b.val -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.id, a.val, b.id, b.val -WHERE b.val = 'val_104' AND b.id = 'Id_2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_1 -POSTHOOK: Output: default@join_result_3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col3 = 'Id_1') and (_col2 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_1 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_3 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.val, a.id, b.id, b.val -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.id, b.val, b.id, a.val -WHERE b.val = 'val_104' AND b.id = 'Id_2' -PREHOOK: type: QUERY -PREHOOK: Input: default@t_a -PREHOOK: Input: default@t_b -PREHOOK: Output: default@join_result_1 -PREHOOK: Output: default@join_result_3 -POSTHOOK: query: explain -FROM T_A a JOIN T_B b ON a.id = b.id -INSERT OVERWRITE TABLE join_result_1 -SELECT a.val, a.id, b.id, b.val -WHERE b.id = 'Id_1' AND b.val = 'val_103' -INSERT OVERWRITE TABLE join_result_3 -SELECT a.id, b.val, b.id, a.val -WHERE b.val = 'val_104' AND b.id = 'Id_2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t_a -POSTHOOK: Input: default@t_b -POSTHOOK: Output: default@join_result_1 -POSTHOOK: Output: default@join_result_3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: id is not null (type: boolean) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col3 = 'Id_1') and (_col2 = 'val_103')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col3 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: ida, vala, idb, valb - Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(ida, 'hll'), compute_stats(vala, 'hll'), compute_stats(idb, 'hll'), compute_stats(valb, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_1 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: ida, vala, idb, valb - Column Types: string, string, string, string - Table: default.join_result_3 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.join_result_3 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - diff --git ql/src/test/results/clientpositive/multi_join_union.q.out ql/src/test/results/clientpositive/multi_join_union.q.out deleted file mode 100644 index ac3fd77714..0000000000 --- ql/src/test/results/clientpositive/multi_join_union.q.out +++ /dev/null @@ -1,187 +0,0 @@ -PREHOOK: query: CREATE TABLE src11 as SELECT * FROM src -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@src11 -POSTHOOK: query: CREATE TABLE src11 as SELECT * FROM src -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src11 -POSTHOOK: Lineage: src11.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src11.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: CREATE TABLE src12 as SELECT * FROM src -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@src12 -POSTHOOK: query: CREATE TABLE src12 as SELECT * FROM src -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src12 -POSTHOOK: Lineage: src12.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src12.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: CREATE TABLE src13 as SELECT * FROM src -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@src13 -POSTHOOK: query: CREATE TABLE src13 as SELECT * FROM src -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src13 -POSTHOOK: Lineage: src13.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src13.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: CREATE TABLE src14 as SELECT * FROM src -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@src14 -POSTHOOK: query: CREATE TABLE src14 as SELECT * FROM src -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src14 -POSTHOOK: Lineage: src14.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src14.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN SELECT * FROM -src11 a JOIN -src12 b ON (a.key = b.key) JOIN -(SELECT * FROM (SELECT * FROM src13 UNION ALL SELECT * FROM src14)a )c ON c.value = b.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src11 -PREHOOK: Input: default@src12 -PREHOOK: Input: default@src13 -PREHOOK: Input: default@src14 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM -src11 a JOIN -src12 b ON (a.key = b.key) JOIN -(SELECT * FROM (SELECT * FROM src13 UNION ALL SELECT * FROM src14)a )c ON c.value = b.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src11 -POSTHOOK: Input: default@src12 -POSTHOOK: Input: default@src13 -POSTHOOK: Input: default@src14 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-6 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-6 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - $hdt$_2:$hdt$_2-subquery1:src13 - Fetch Operator - limit: -1 - $hdt$_2:$hdt$_2-subquery2:src14 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_2:$hdt$_2-subquery1:src13 - TableScan - alias: src13 - filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col3 (type: string) - 1 _col1 (type: string) - $hdt$_2:$hdt$_2-subquery2:src14 - TableScan - alias: src14 - filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col3 (type: string) - 1 _col1 (type: string) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2576 Data size: 1375584 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2576 Data size: 1375584 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/multigroupby_singlemr.q.out ql/src/test/results/clientpositive/multigroupby_singlemr.q.out deleted file mode 100644 index 3ae1152645..0000000000 --- ql/src/test/results/clientpositive/multigroupby_singlemr.q.out +++ /dev/null @@ -1,1303 +0,0 @@ -PREHOOK: query: CREATE TABLE TBL_n0(C1 INT, C2 INT, C3 INT, C4 INT) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@TBL_n0 -POSTHOOK: query: CREATE TABLE TBL_n0(C1 INT, C2 INT, C3 INT, C4 INT) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@TBL_n0 -PREHOOK: query: CREATE TABLE DEST1_n116(d1 INT, d2 INT) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@DEST1_n116 -POSTHOOK: query: CREATE TABLE DEST1_n116(d1 INT, d2 INT) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@DEST1_n116 -PREHOOK: query: CREATE TABLE DEST2_n30(d1 INT, d2 INT, d3 INT) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@DEST2_n30 -POSTHOOK: query: CREATE TABLE DEST2_n30(d1 INT, d2 INT, d3 INT) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@DEST2_n30 -PREHOOK: query: CREATE TABLE DEST3_n4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@DEST3_n4 -POSTHOOK: query: CREATE TABLE DEST3_n4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@DEST3_n4 -PREHOOK: query: CREATE TABLE DEST4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@DEST4 -POSTHOOK: query: CREATE TABLE DEST4(d1 INT, d2 INT, d3 INT, d4 INT) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@DEST4 -PREHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_n0 -PREHOOK: Output: default@dest1_n116 -PREHOOK: Output: default@dest2_n30 -POSTHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_n0 -POSTHOOK: Output: default@dest1_n116 -POSTHOOK: Output: default@dest2_n30 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-7 - Stage-4 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-1, Stage-4, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-5 - Stage-7 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: tbl_n0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int), c2 (type: int) - outputColumnNames: c1, c2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c2) - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Select Operator - expressions: c1 (type: int), c2 (type: int), c3 (type: int) - outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c3) - keys: c1 (type: int), c2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n116 - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: d1, d2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n116 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2 - Column Types: int, int - Table: default.dest1_n116 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3 - Column Types: int, int, int - Table: default.dest2_n30 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) - outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C2, TBL_n0.C1 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_n0 -PREHOOK: Output: default@dest1_n116 -PREHOOK: Output: default@dest2_n30 -POSTHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C2, TBL_n0.C1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_n0 -POSTHOOK: Output: default@dest1_n116 -POSTHOOK: Output: default@dest2_n30 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-7 - Stage-4 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-1, Stage-4, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-5 - Stage-7 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: tbl_n0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int), c2 (type: int) - outputColumnNames: c1, c2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c2) - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Select Operator - expressions: c1 (type: int), c2 (type: int), c3 (type: int) - outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c3) - keys: c2 (type: int), c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n116 - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: d1, d2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n116 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2 - Column Types: int, int - Table: default.dest1_n116 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 860 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 892 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3 - Column Types: int, int, int - Table: default.dest2_n30 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: int), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) - outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1332 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_n0 -PREHOOK: Output: default@dest2_n30 -PREHOOK: Output: default@dest3_n4 -POSTHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_n0 -POSTHOOK: Output: default@dest2_n30 -POSTHOOK: Output: default@dest3_n4 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-7 - Stage-4 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-1, Stage-4, Stage-7 - Stage-5 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-5 - Stage-7 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: tbl_n0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) - outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c4) - keys: c1 (type: int), c2 (type: int), c3 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint) - Select Operator - expressions: c1 (type: int), c2 (type: int), c3 (type: int) - outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c3) - keys: c1 (type: int), c2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest3_n4 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest3_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3, d4 - Column Types: int, int, int, int - Table: default.dest3_n4 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3 - Column Types: int, int, int - Table: default.dest2_n30 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) - outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 -INSERT OVERWRITE TABLE DEST4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C3, TBL_n0.C2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_n0 -PREHOOK: Output: default@dest3_n4 -PREHOOK: Output: default@dest4 -POSTHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 -INSERT OVERWRITE TABLE DEST4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C3, TBL_n0.C2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_n0 -POSTHOOK: Output: default@dest3_n4 -POSTHOOK: Output: default@dest4 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-4, Stage-6 - Stage-4 depends on stages: Stage-2 - Stage-5 depends on stages: Stage-1, Stage-4, Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-6 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: tbl_n0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) - outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: c1 (type: int), c2 (type: int), c3 (type: int) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: c1 (type: int), c2 (type: int), c3 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: c4 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Forward - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) - mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest3_n4 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col2 (type: int), KEY._col1 (type: int) - mode: complete - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), UDFToInteger(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest4 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest3_n4 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3, d4 - Column Types: int, int, int, int - Table: default.dest3_n4 - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3, d4 - Column Types: int, int, int, int - Table: default.dest4 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest4 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 -INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_n0 -PREHOOK: Output: default@dest1_n116 -PREHOOK: Output: default@dest2_n30 -PREHOOK: Output: default@dest3_n4 -POSTHOOK: query: EXPLAIN -FROM TBL_n0 -INSERT OVERWRITE TABLE DEST3_n4 SELECT TBL_n0.C1, TBL_n0.C2, TBL_n0.C3, COUNT(TBL_n0.C4) GROUP BY TBL_n0.C1, TBL_n0.C2, TBL_n0.C3 -INSERT OVERWRITE TABLE DEST2_n30 SELECT TBL_n0.C1, TBL_n0.C2, COUNT(TBL_n0.C3) GROUP BY TBL_n0.C1, TBL_n0.C2 -INSERT OVERWRITE TABLE DEST1_n116 SELECT TBL_n0.C1, COUNT(TBL_n0.C2) GROUP BY TBL_n0.C1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_n0 -POSTHOOK: Output: default@dest1_n116 -POSTHOOK: Output: default@dest2_n30 -POSTHOOK: Output: default@dest3_n4 -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-0 depends on stages: Stage-3 - Stage-4 depends on stages: Stage-0, Stage-5, Stage-8, Stage-11 - Stage-5 depends on stages: Stage-3 - Stage-7 depends on stages: Stage-1, Stage-5, Stage-8, Stage-11 - Stage-10 depends on stages: Stage-2, Stage-5, Stage-8, Stage-11 - Stage-6 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-6 - Stage-8 depends on stages: Stage-6 - Stage-9 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-9 - Stage-11 depends on stages: Stage-9 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: tbl_n0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int), c2 (type: int), c3 (type: int), c4 (type: int) - outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c4) - keys: c1 (type: int), c2 (type: int), c3 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint) - Select Operator - expressions: c1 (type: int), c2 (type: int), c3 (type: int) - outputColumnNames: c1, c2, c3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c3) - keys: c1 (type: int), c2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Select Operator - expressions: c1 (type: int), c2 (type: int) - outputColumnNames: c1, c2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(c2) - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), UDFToInteger(_col3) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest3_n4 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) - outputColumnNames: d1, d2, d3, d4 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll'), compute_stats(d4, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest3_n4 - - Stage: Stage-4 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3, d4 - Column Types: int, int, int, int - Table: default.dest3_n4 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1712 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1776 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2, d3 - Column Types: int, int, int - Table: default.dest2_n30 - - Stage: Stage-10 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: d1, d2 - Column Types: int, int - Table: default.dest1_n116 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), UDFToInteger(_col2) (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) - outputColumnNames: d1, d2, d3 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll'), compute_stats(d3, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2_n30 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1336 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n116 - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: d1, d2 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(d1, 'hll'), compute_stats(d2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n116 - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 896 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 896 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - diff --git ql/src/test/results/clientpositive/nested_column_pruning.q.out ql/src/test/results/clientpositive/nested_column_pruning.q.out deleted file mode 100644 index 233995910c..0000000000 --- ql/src/test/results/clientpositive/nested_column_pruning.q.out +++ /dev/null @@ -1,1999 +0,0 @@ -PREHOOK: query: DROP TABLE IF EXISTS dummy_n5 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS dummy_n5 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE dummy_n5 (i int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dummy_n5 -POSTHOOK: query: CREATE TABLE dummy_n5 (i int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dummy_n5 -PREHOOK: query: INSERT INTO TABLE dummy_n5 VALUES (42) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@dummy_n5 -POSTHOOK: query: INSERT INTO TABLE dummy_n5 VALUES (42) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@dummy_n5 -POSTHOOK: Lineage: dummy_n5.i SCRIPT [] -PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE nested_tbl_1_n1 ( - a int, - s1 struct, f6: int>, - s2 struct, f11: map>>, - s3 struct>>, - s4 map>, - s5 struct>>>, - s6 map>>>> -) STORED AS PARQUET -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@nested_tbl_1_n1 -POSTHOOK: query: CREATE TABLE nested_tbl_1_n1 ( - a int, - s1 struct, f6: int>, - s2 struct, f11: map>>, - s3 struct>>, - s4 map>, - s5 struct>>>, - s6 map>>>> -) STORED AS PARQUET -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nested_tbl_1_n1 -PREHOOK: query: INSERT INTO TABLE nested_tbl_1_n1 SELECT - 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), - named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), - named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), - map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), - named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), - map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), - 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) -FROM dummy_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@dummy_n5 -PREHOOK: Output: default@nested_tbl_1_n1 -POSTHOOK: query: INSERT INTO TABLE nested_tbl_1_n1 SELECT - 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), - named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), - named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), - map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), - named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), - map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), - 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) -FROM dummy_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dummy_n5 -POSTHOOK: Output: default@nested_tbl_1_n1 -POSTHOOK: Lineage: nested_tbl_1_n1.a SIMPLE [] -POSTHOOK: Lineage: nested_tbl_1_n1.s1 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n1.s2 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n1.s3 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n1.s4 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n1.s5 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n1.s6 EXPRESSION [] -PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE nested_tbl_2_n1 LIKE nested_tbl_1_n1 -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@nested_tbl_2_n1 -POSTHOOK: query: CREATE TABLE nested_tbl_2_n1 LIKE nested_tbl_1_n1 -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nested_tbl_2_n1 -PREHOOK: query: INSERT INTO TABLE nested_tbl_2_n1 SELECT - 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), - named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), - named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), - map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), - named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), - map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), - 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) -FROM dummy_n5 -PREHOOK: type: QUERY -PREHOOK: Input: default@dummy_n5 -PREHOOK: Output: default@nested_tbl_2_n1 -POSTHOOK: query: INSERT INTO TABLE nested_tbl_2_n1 SELECT - 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), - named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), - named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), - map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), - named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), - map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), - 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) -FROM dummy_n5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dummy_n5 -POSTHOOK: Output: default@nested_tbl_2_n1 -POSTHOOK: Lineage: nested_tbl_2_n1.a SIMPLE [] -POSTHOOK: Lineage: nested_tbl_2_n1.s1 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n1.s2 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n1.s3 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n1.s4 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n1.s5 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n1.s6 EXPRESSION [] -PREHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: a (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -1 -PREHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f1 (type: boolean) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -false -PREHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f1, s1.f2 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f1 (type: boolean), s1.f2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -false foo -PREHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -{"f4":4,"f5":5.0} 4 -PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f3.f5 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -5.0 -PREHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f3.f4, s2.f8.f9 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f4 (type: int), s2.f8.f9 (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -4 true -PREHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - filterExpr: (not s1.f1) (type: boolean) - Pruned Column Paths: s1.f2, s1.f1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not s1.f1) (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n1 WHERE s1.f1 = FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -foo -PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - filterExpr: (s1.f3.f4 = 4) (type: boolean) - Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f3.f4 = 4) (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n1 WHERE s1.f3.f4 = 4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -5.0 -PREHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - filterExpr: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) - Pruned Column Paths: s1.f2, s2.f8 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s2.f8 (type: struct,f11:map>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n1 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -{"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} -PREHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n1 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n1 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s2.f8.f10 - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s3 (type: struct>>) - outputColumnNames: s3 - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int) - outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col3.f12 (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: s2.f8.f10 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int) - outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col3.f12 (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n1 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n1 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -10 {"f13":"foo","f14":14} -10 {"f13":"bar","f14":28} -11 {"f13":"foo","f14":14} -11 {"f13":"bar","f14":28} -PREHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s2.f8.f10, s1.f3.f4 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (s2.f8.f10[1] pmod s1.f3.f4) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -3 -PREHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f5 (type: double), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: double) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: double) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: double) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3.f5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -5.0 1 -PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: struct) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: struct) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: struct) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -{"f4":4,"f5":5.0} 1 -PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: struct) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: struct) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: struct) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: struct) - null sort order: z - sort order: + - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n1 GROUP BY s1.f3 ORDER BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -{"f4":4,"f5":5.0} 1 -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -PREHOOK: Input: default@nested_tbl_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -POSTHOOK: Input: default@nested_tbl_2_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f3.f4 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f6 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0.f3.f4 (type: int) - 1 _col0.f6 (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -PREHOOK: Input: default@nested_tbl_2_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_2_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -POSTHOOK: Input: default@nested_tbl_2_n1 -#### A masked pattern was here #### -5.0 {"f9":false,"f10":[20,22],"f11":{"key3":true,"key4":false}} -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f3.f4 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: (s1.f6 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f6 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f6 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0.f3.f4 (type: int) - 1 _col0.f6 (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n1 t1 JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -5.0 {"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), true (type: boolean) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: int), true (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) - Pruned Column Paths: s1.f6, s2.f8.f9 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f6 (type: int), s2.f8.f9 (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: boolean) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: boolean) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int), true (type: boolean) - 1 _col0 (type: int), _col1 (type: boolean) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -5.0 -Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s2 (type: struct,f11:map>>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - residual filter predicates: {(_col0.f1 <> _col1.f8.f9)} - Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -5.0 -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: s1.f6 is not null (type: boolean) - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f6 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s2 (type: struct,f11:map>>), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col0, _col2 - residual filter predicates: {(_col0.f1 <> _col2.f8.f9)} - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n1 t1 LEFT SEMI JOIN nested_tbl_1_n1 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -5.0 -PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE nested_tbl_3_n1 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS PARQUET -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@nested_tbl_3_n1 -POSTHOOK: query: CREATE TABLE nested_tbl_3_n1 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS PARQUET -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nested_tbl_3_n1 -PREHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n1 PARTITION(f3) -SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 -FROM nested_tbl_1_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -PREHOOK: Output: default@nested_tbl_3_n1 -POSTHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n1 PARTITION(f3) -SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 -FROM nested_tbl_1_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -POSTHOOK: Output: default@nested_tbl_3_n1@f3=4 -POSTHOOK: Lineage: nested_tbl_3_n1 PARTITION(f3=4).f1 EXPRESSION [(nested_tbl_1_n1)nested_tbl_1_n1.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] -POSTHOOK: Lineage: nested_tbl_3_n1 PARTITION(f3=4).f2 EXPRESSION [(nested_tbl_1_n1)nested_tbl_1_n1.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] -PREHOOK: query: SELECT * FROM nested_tbl_3_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_3_n1 -PREHOOK: Input: default@nested_tbl_3_n1@f3=4 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM nested_tbl_3_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_3_n1 -POSTHOOK: Input: default@nested_tbl_3_n1@f3=4 -#### A masked pattern was here #### -false foo 4 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n1 -GROUP BY s3.f12[0].f14 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n1 -GROUP BY s3.f12[0].f14 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s3.f12, s1.f6 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s3.f12[0].f14 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n1 -GROUP BY s3.f12[0].f14 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n1 -GROUP BY s3.f12[0].f14 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -1 14 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n1 -GROUP BY s4['key1'].f15 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n1 -GROUP BY s4['key1'].f15 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s4['key1'].f15 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n1 -GROUP BY s4['key1'].f15 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n1 -GROUP BY s4['key1'].f15 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -1 1 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16[0].f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16[0].f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s5.f16, s1.f6 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s5.f16[0].f18.f19 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16[0].f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16[0].f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -1 14 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16.f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16.f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f6, s5.f16 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s5 (type: struct>>>) - outputColumnNames: s1, s5 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(s1.f6) - keys: s5.f16.f18.f19 (type: array) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: array) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: array) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16.f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n1 -GROUP BY s5.f16.f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -1 [14,28] -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20[0].f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20[0].f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s6['key1'].f20[0].f21.f22 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20[0].f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20[0].f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -1 1 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20.f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20.f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n1 - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s6 (type: map>>>>) - outputColumnNames: s1, s6 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(s1.f6) - keys: s6['key1'].f20.f21.f22 (type: array) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: array) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: array) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20.f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n1 -GROUP BY s6['key1'].f20.f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n1 -#### A masked pattern was here #### -1 [1] diff --git ql/src/test/results/clientpositive/no_hooks.q.out ql/src/test/results/clientpositive/no_hooks.q.out deleted file mode 100644 index 7583863800..0000000000 --- ql/src/test/results/clientpositive/no_hooks.q.out +++ /dev/null @@ -1,197 +0,0 @@ -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -POSTHOOK: query: EXPLAIN -SELECT * FROM src src1 JOIN src src2 WHERE src1.key < 10 and src2.key < 10 SORT BY src1.key, src1.value, src2.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: src2 - filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - sort order: ++++ - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -POSTHOOK: query: SELECT * FROM src src1 JOIN src src2 WHERE src1.key < 10 and src2.key < 10 SORT BY src1.key, src1.value, src2.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 9 val_9 -0 val_0 9 val_9 -0 val_0 9 val_9 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 2 val_2 -2 val_2 4 val_4 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 8 val_8 -2 val_2 9 val_9 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 2 val_2 -4 val_4 4 val_4 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 8 val_8 -4 val_4 9 val_9 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 9 val_9 -5 val_5 9 val_9 -5 val_5 9 val_9 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 2 val_2 -8 val_8 4 val_4 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 8 val_8 -8 val_8 9 val_9 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 2 val_2 -9 val_9 4 val_4 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 8 val_8 -9 val_9 9 val_9 diff --git ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out deleted file mode 100644 index 96b7c0a7d2..0000000000 --- ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out +++ /dev/null @@ -1,356 +0,0 @@ -PREHOOK: query: explain select nkey, nkey + 1 from (select key + 1 as nkey, value from src) a -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select nkey, nkey + 1 from (select key + 1 as nkey, value from src) a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToDouble(key) + 1.0D) (type: double), ((UDFToDouble(key) + 1.0D) + 1.0D) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### - 25 - 25 - 25 - 25 - val_165 25 - val_193 25 - val_265 25 - val_27 25 - val_409 25 - val_484 25 -128 25 -146 val_146 25 -150 val_150 25 -213 val_213 25 -224 25 -238 val_238 25 -255 val_255 25 -273 val_273 25 -278 val_278 25 -311 val_311 25 -369 25 -401 val_401 25 -406 val_406 25 -66 val_66 25 -98 val_98 25 -Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-3:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-4 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-4 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:src1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:src1 - TableScan - alias: src1 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 - 1 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-3:MAPRED' is a cross product -PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count -FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count - FROM (SELECT * - FROM (SELECT key, value - FROM src1) tmp1 ) tmp2 - JOIN (SELECT count(*) as count - FROM src1) tmp3 - ) tmp4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### - 25 - 25 - 25 - 25 - val_165 25 - val_193 25 - val_265 25 - val_27 25 - val_409 25 - val_484 25 -128 25 -146 val_146 25 -150 val_150 25 -213 val_213 25 -224 25 -238 val_238 25 -255 val_255 25 -273 val_273 25 -278 val_278 25 -311 val_311 25 -369 25 -401 val_401 25 -406 val_406 25 -66 val_66 25 -98 val_98 25 diff --git ql/src/test/results/clientpositive/notable_alias1.q.out ql/src/test/results/clientpositive/notable_alias1.q.out deleted file mode 100644 index 258840619b..0000000000 --- ql/src/test/results/clientpositive/notable_alias1.q.out +++ /dev/null @@ -1,208 +0,0 @@ -PREHOOK: query: CREATE TABLE dest1_n4(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest1_n4 -POSTHOOK: query: CREATE TABLE dest1_n4(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest1_n4 -PREHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1_n4 -POSTHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1_n4 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n4 - Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) - outputColumnNames: dummy, key, value - Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(dummy, 'hll'), compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n4 - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: dummy, key, value - Column Types: string, int, double - Table: default.dest1_n4 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1_n4 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE dest1_n4 SELECT '1234', key, count(1) WHERE src.key < 100 group by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1_n4 -POSTHOOK: Lineage: dest1_n4.dummy SIMPLE [] -POSTHOOK: Lineage: dest1_n4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_n4.value EXPRESSION [(src)src.null, ] -PREHOOK: query: SELECT dest1_n4.* FROM dest1_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1_n4 -#### A masked pattern was here #### -POSTHOOK: query: SELECT dest1_n4.* FROM dest1_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1_n4 -#### A masked pattern was here #### -1234 0 3.0 -1234 10 1.0 -1234 11 1.0 -1234 12 2.0 -1234 15 2.0 -1234 17 1.0 -1234 18 2.0 -1234 19 1.0 -1234 2 1.0 -1234 20 1.0 -1234 24 2.0 -1234 26 2.0 -1234 27 1.0 -1234 28 1.0 -1234 30 1.0 -1234 33 1.0 -1234 34 1.0 -1234 35 3.0 -1234 37 2.0 -1234 4 1.0 -1234 41 1.0 -1234 42 2.0 -1234 43 1.0 -1234 44 1.0 -1234 47 1.0 -1234 5 3.0 -1234 51 2.0 -1234 53 1.0 -1234 54 1.0 -1234 57 1.0 -1234 58 2.0 -1234 64 1.0 -1234 65 1.0 -1234 66 1.0 -1234 67 2.0 -1234 69 1.0 -1234 70 3.0 -1234 72 2.0 -1234 74 1.0 -1234 76 2.0 -1234 77 1.0 -1234 78 1.0 -1234 8 1.0 -1234 80 1.0 -1234 82 1.0 -1234 83 2.0 -1234 84 2.0 -1234 85 1.0 -1234 86 1.0 -1234 87 1.0 -1234 9 1.0 -1234 90 3.0 -1234 92 1.0 -1234 95 2.0 -1234 96 1.0 -1234 97 2.0 -1234 98 2.0 diff --git ql/src/test/results/clientpositive/notable_alias2.q.out ql/src/test/results/clientpositive/notable_alias2.q.out deleted file mode 100644 index 919c86243b..0000000000 --- ql/src/test/results/clientpositive/notable_alias2.q.out +++ /dev/null @@ -1,208 +0,0 @@ -PREHOOK: query: CREATE TABLE dest1_n50(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest1_n50 -POSTHOOK: query: CREATE TABLE dest1_n50(dummy STRING, key INT, value DOUBLE) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest1_n50 -PREHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1_n50 -POSTHOOK: query: EXPLAIN -FROM src -INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1_n50 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: '1234' (type: string), UDFToInteger(_col0) (type: int), UDFToDouble(_col1) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n50 - Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) - outputColumnNames: dummy, key, value - Statistics: Num rows: 83 Data size: 8300 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(dummy, 'hll'), compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n50 - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: dummy, key, value - Column Types: string, int, double - Table: default.dest1_n50 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1_n50 -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE dest1_n50 SELECT '1234', src.key, count(1) WHERE key < 100 group by src.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1_n50 -POSTHOOK: Lineage: dest1_n50.dummy SIMPLE [] -POSTHOOK: Lineage: dest1_n50.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_n50.value EXPRESSION [(src)src.null, ] -PREHOOK: query: SELECT dest1_n50.* FROM dest1_n50 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1_n50 -#### A masked pattern was here #### -POSTHOOK: query: SELECT dest1_n50.* FROM dest1_n50 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1_n50 -#### A masked pattern was here #### -1234 0 3.0 -1234 10 1.0 -1234 11 1.0 -1234 12 2.0 -1234 15 2.0 -1234 17 1.0 -1234 18 2.0 -1234 19 1.0 -1234 2 1.0 -1234 20 1.0 -1234 24 2.0 -1234 26 2.0 -1234 27 1.0 -1234 28 1.0 -1234 30 1.0 -1234 33 1.0 -1234 34 1.0 -1234 35 3.0 -1234 37 2.0 -1234 4 1.0 -1234 41 1.0 -1234 42 2.0 -1234 43 1.0 -1234 44 1.0 -1234 47 1.0 -1234 5 3.0 -1234 51 2.0 -1234 53 1.0 -1234 54 1.0 -1234 57 1.0 -1234 58 2.0 -1234 64 1.0 -1234 65 1.0 -1234 66 1.0 -1234 67 2.0 -1234 69 1.0 -1234 70 3.0 -1234 72 2.0 -1234 74 1.0 -1234 76 2.0 -1234 77 1.0 -1234 78 1.0 -1234 8 1.0 -1234 80 1.0 -1234 82 1.0 -1234 83 2.0 -1234 84 2.0 -1234 85 1.0 -1234 86 1.0 -1234 87 1.0 -1234 9 1.0 -1234 90 3.0 -1234 92 1.0 -1234 95 2.0 -1234 96 1.0 -1234 97 2.0 -1234 98 2.0 diff --git ql/src/test/results/clientpositive/nullgroup.q.out ql/src/test/results/clientpositive/nullgroup.q.out deleted file mode 100644 index 4d1517e039..0000000000 --- ql/src/test/results/clientpositive/nullgroup.q.out +++ /dev/null @@ -1,278 +0,0 @@ -PREHOOK: query: explain -select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: final - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 -PREHOOK: query: explain -select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 -PREHOOK: query: explain -select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Group By Operator - aggregations: count() - mode: partial1 - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: final - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 -PREHOOK: query: explain -select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Group By Operator - aggregations: count() - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1) from src x where x.key > 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1) from src x where x.key > 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 diff --git ql/src/test/results/clientpositive/nullgroup2.q.out ql/src/test/results/clientpositive/nullgroup2.q.out deleted file mode 100644 index ea8cc08ab0..0000000000 --- ql/src/test/results/clientpositive/nullgroup2.q.out +++ /dev/null @@ -1,314 +0,0 @@ -PREHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: partials - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: partial1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 9999.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count() - keys: KEY._col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select x.key, count(1) from src x where x.key > 9999 group by x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/nullgroup4.q.out ql/src/test/results/clientpositive/nullgroup4.q.out deleted file mode 100644 index 8797fa0ee2..0000000000 --- ql/src/test/results/clientpositive/nullgroup4.q.out +++ /dev/null @@ -1,353 +0,0 @@ -PREHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(DISTINCT value) - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 125 Data size: 13375 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 13375 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0) - mode: partials - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 0 -PREHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: partial2 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 12375 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1), count(_col0) - mode: partial2 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 0 -PREHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: value (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: value (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(), count(DISTINCT KEY._col0:0._col0) - mode: partial1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: final - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 0 -PREHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: value (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(), count(DISTINCT KEY._col0:0._col0) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1), count(distinct x.value) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 0 diff --git ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out deleted file mode 100644 index 09c59d395e..0000000000 --- ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out +++ /dev/null @@ -1,136 +0,0 @@ -PREHOOK: query: explain -select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(DISTINCT _col0), count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 125 Data size: 25125 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Statistics: Num rows: 125 Data size: 25125 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 0 0 -PREHOOK: query: explain -select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 9999.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) - mode: complete - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select count(1), count(distinct x.value), count(distinct substr(x.value, 5)) from src x where x.key = 9999 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 0 0 diff --git ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out deleted file mode 100644 index 5b20c2b1a9..0000000000 --- ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out +++ /dev/null @@ -1,3756 +0,0 @@ -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` -FROM `default`.`srcpart` -ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` -LIMIT 10 -OFFSET 400 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 410 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Offset of rows: 400 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -189 189 2008-04-08 11 -189 189 2008-04-08 12 -189 189 2008-04-09 11 -189 189 2008-04-09 12 -19 19 2008-04-08 11 -19 19 2008-04-08 12 -19 19 2008-04-09 11 -19 19 2008-04-09 12 -190 190 2008-04-08 11 -190 190 2008-04-08 12 -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` -FROM `default`.`srcpart` -ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` -LIMIT 10 -OFFSET 490 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 500 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Offset of rows: 490 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -201 201 2008-04-09 11 -201 201 2008-04-09 12 -202 202 2008-04-08 11 -202 202 2008-04-08 12 -202 202 2008-04-09 11 -202 202 2008-04-09 12 -203 203 2008-04-08 11 -203 203 2008-04-08 11 -203 203 2008-04-08 12 -203 203 2008-04-08 12 -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` -FROM `default`.`srcpart` -ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` -LIMIT 20 -OFFSET 490 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 510 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Offset of rows: 490 - Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -201 201 2008-04-09 11 -201 201 2008-04-09 12 -202 202 2008-04-08 11 -202 202 2008-04-08 12 -202 202 2008-04-09 11 -202 202 2008-04-09 12 -203 203 2008-04-08 11 -203 203 2008-04-08 11 -203 203 2008-04-08 12 -203 203 2008-04-08 12 -203 203 2008-04-09 11 -203 203 2008-04-09 11 -203 203 2008-04-09 12 -203 203 2008-04-09 12 -205 205 2008-04-08 11 -205 205 2008-04-08 11 -205 205 2008-04-08 12 -205 205 2008-04-08 12 -205 205 2008-04-09 11 -205 205 2008-04-09 11 -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, SUBSTR(`value`, 5) AS `csubstr`, `ds`, `hr` -FROM `default`.`srcpart` -ORDER BY `key`, SUBSTR(`value`, 5), `ds`, `hr` -LIMIT 600 -OFFSET 490 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 1090 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 600 - Offset of rows: 490 - Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 600 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -201 201 2008-04-09 11 -201 201 2008-04-09 12 -202 202 2008-04-08 11 -202 202 2008-04-08 12 -202 202 2008-04-09 11 -202 202 2008-04-09 12 -203 203 2008-04-08 11 -203 203 2008-04-08 11 -203 203 2008-04-08 12 -203 203 2008-04-08 12 -203 203 2008-04-09 11 -203 203 2008-04-09 11 -203 203 2008-04-09 12 -203 203 2008-04-09 12 -205 205 2008-04-08 11 -205 205 2008-04-08 11 -205 205 2008-04-08 12 -205 205 2008-04-08 12 -205 205 2008-04-09 11 -205 205 2008-04-09 11 -205 205 2008-04-09 12 -205 205 2008-04-09 12 -207 207 2008-04-08 11 -207 207 2008-04-08 11 -207 207 2008-04-08 12 -207 207 2008-04-08 12 -207 207 2008-04-09 11 -207 207 2008-04-09 11 -207 207 2008-04-09 12 -207 207 2008-04-09 12 -208 208 2008-04-08 11 -208 208 2008-04-08 11 -208 208 2008-04-08 11 -208 208 2008-04-08 12 -208 208 2008-04-08 12 -208 208 2008-04-08 12 -208 208 2008-04-09 11 -208 208 2008-04-09 11 -208 208 2008-04-09 11 -208 208 2008-04-09 12 -208 208 2008-04-09 12 -208 208 2008-04-09 12 -209 209 2008-04-08 11 -209 209 2008-04-08 11 -209 209 2008-04-08 12 -209 209 2008-04-08 12 -209 209 2008-04-09 11 -209 209 2008-04-09 11 -209 209 2008-04-09 12 -209 209 2008-04-09 12 -213 213 2008-04-08 11 -213 213 2008-04-08 11 -213 213 2008-04-08 12 -213 213 2008-04-08 12 -213 213 2008-04-09 11 -213 213 2008-04-09 11 -213 213 2008-04-09 12 -213 213 2008-04-09 12 -214 214 2008-04-08 11 -214 214 2008-04-08 12 -214 214 2008-04-09 11 -214 214 2008-04-09 12 -216 216 2008-04-08 11 -216 216 2008-04-08 11 -216 216 2008-04-08 12 -216 216 2008-04-08 12 -216 216 2008-04-09 11 -216 216 2008-04-09 11 -216 216 2008-04-09 12 -216 216 2008-04-09 12 -217 217 2008-04-08 11 -217 217 2008-04-08 11 -217 217 2008-04-08 12 -217 217 2008-04-08 12 -217 217 2008-04-09 11 -217 217 2008-04-09 11 -217 217 2008-04-09 12 -217 217 2008-04-09 12 -218 218 2008-04-08 11 -218 218 2008-04-08 12 -218 218 2008-04-09 11 -218 218 2008-04-09 12 -219 219 2008-04-08 11 -219 219 2008-04-08 11 -219 219 2008-04-08 12 -219 219 2008-04-08 12 -219 219 2008-04-09 11 -219 219 2008-04-09 11 -219 219 2008-04-09 12 -219 219 2008-04-09 12 -221 221 2008-04-08 11 -221 221 2008-04-08 11 -221 221 2008-04-08 12 -221 221 2008-04-08 12 -221 221 2008-04-09 11 -221 221 2008-04-09 11 -221 221 2008-04-09 12 -221 221 2008-04-09 12 -222 222 2008-04-08 11 -222 222 2008-04-08 12 -222 222 2008-04-09 11 -222 222 2008-04-09 12 -223 223 2008-04-08 11 -223 223 2008-04-08 11 -223 223 2008-04-08 12 -223 223 2008-04-08 12 -223 223 2008-04-09 11 -223 223 2008-04-09 11 -223 223 2008-04-09 12 -223 223 2008-04-09 12 -224 224 2008-04-08 11 -224 224 2008-04-08 11 -224 224 2008-04-08 12 -224 224 2008-04-08 12 -224 224 2008-04-09 11 -224 224 2008-04-09 11 -224 224 2008-04-09 12 -224 224 2008-04-09 12 -226 226 2008-04-08 11 -226 226 2008-04-08 12 -226 226 2008-04-09 11 -226 226 2008-04-09 12 -228 228 2008-04-08 11 -228 228 2008-04-08 12 -228 228 2008-04-09 11 -228 228 2008-04-09 12 -229 229 2008-04-08 11 -229 229 2008-04-08 11 -229 229 2008-04-08 12 -229 229 2008-04-08 12 -229 229 2008-04-09 11 -229 229 2008-04-09 11 -229 229 2008-04-09 12 -229 229 2008-04-09 12 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -233 233 2008-04-08 11 -233 233 2008-04-08 11 -233 233 2008-04-08 12 -233 233 2008-04-08 12 -233 233 2008-04-09 11 -233 233 2008-04-09 11 -233 233 2008-04-09 12 -233 233 2008-04-09 12 -235 235 2008-04-08 11 -235 235 2008-04-08 12 -235 235 2008-04-09 11 -235 235 2008-04-09 12 -237 237 2008-04-08 11 -237 237 2008-04-08 11 -237 237 2008-04-08 12 -237 237 2008-04-08 12 -237 237 2008-04-09 11 -237 237 2008-04-09 11 -237 237 2008-04-09 12 -237 237 2008-04-09 12 -238 238 2008-04-08 11 -238 238 2008-04-08 11 -238 238 2008-04-08 12 -238 238 2008-04-08 12 -238 238 2008-04-09 11 -238 238 2008-04-09 11 -238 238 2008-04-09 12 -238 238 2008-04-09 12 -239 239 2008-04-08 11 -239 239 2008-04-08 11 -239 239 2008-04-08 12 -239 239 2008-04-08 12 -239 239 2008-04-09 11 -239 239 2008-04-09 11 -239 239 2008-04-09 12 -239 239 2008-04-09 12 -24 24 2008-04-08 11 -24 24 2008-04-08 11 -24 24 2008-04-08 12 -24 24 2008-04-08 12 -24 24 2008-04-09 11 -24 24 2008-04-09 11 -24 24 2008-04-09 12 -24 24 2008-04-09 12 -241 241 2008-04-08 11 -241 241 2008-04-08 12 -241 241 2008-04-09 11 -241 241 2008-04-09 12 -242 242 2008-04-08 11 -242 242 2008-04-08 11 -242 242 2008-04-08 12 -242 242 2008-04-08 12 -242 242 2008-04-09 11 -242 242 2008-04-09 11 -242 242 2008-04-09 12 -242 242 2008-04-09 12 -244 244 2008-04-08 11 -244 244 2008-04-08 12 -244 244 2008-04-09 11 -244 244 2008-04-09 12 -247 247 2008-04-08 11 -247 247 2008-04-08 12 -247 247 2008-04-09 11 -247 247 2008-04-09 12 -248 248 2008-04-08 11 -248 248 2008-04-08 12 -248 248 2008-04-09 11 -248 248 2008-04-09 12 -249 249 2008-04-08 11 -249 249 2008-04-08 12 -249 249 2008-04-09 11 -249 249 2008-04-09 12 -252 252 2008-04-08 11 -252 252 2008-04-08 12 -252 252 2008-04-09 11 -252 252 2008-04-09 12 -255 255 2008-04-08 11 -255 255 2008-04-08 11 -255 255 2008-04-08 12 -255 255 2008-04-08 12 -255 255 2008-04-09 11 -255 255 2008-04-09 11 -255 255 2008-04-09 12 -255 255 2008-04-09 12 -256 256 2008-04-08 11 -256 256 2008-04-08 11 -256 256 2008-04-08 12 -256 256 2008-04-08 12 -256 256 2008-04-09 11 -256 256 2008-04-09 11 -256 256 2008-04-09 12 -256 256 2008-04-09 12 -257 257 2008-04-08 11 -257 257 2008-04-08 12 -257 257 2008-04-09 11 -257 257 2008-04-09 12 -258 258 2008-04-08 11 -258 258 2008-04-08 12 -258 258 2008-04-09 11 -258 258 2008-04-09 12 -26 26 2008-04-08 11 -26 26 2008-04-08 11 -26 26 2008-04-08 12 -26 26 2008-04-08 12 -26 26 2008-04-09 11 -26 26 2008-04-09 11 -26 26 2008-04-09 12 -26 26 2008-04-09 12 -260 260 2008-04-08 11 -260 260 2008-04-08 12 -260 260 2008-04-09 11 -260 260 2008-04-09 12 -262 262 2008-04-08 11 -262 262 2008-04-08 12 -262 262 2008-04-09 11 -262 262 2008-04-09 12 -263 263 2008-04-08 11 -263 263 2008-04-08 12 -263 263 2008-04-09 11 -263 263 2008-04-09 12 -265 265 2008-04-08 11 -265 265 2008-04-08 11 -265 265 2008-04-08 12 -265 265 2008-04-08 12 -265 265 2008-04-09 11 -265 265 2008-04-09 11 -265 265 2008-04-09 12 -265 265 2008-04-09 12 -266 266 2008-04-08 11 -266 266 2008-04-08 12 -266 266 2008-04-09 11 -266 266 2008-04-09 12 -27 27 2008-04-08 11 -27 27 2008-04-08 12 -27 27 2008-04-09 11 -27 27 2008-04-09 12 -272 272 2008-04-08 11 -272 272 2008-04-08 11 -272 272 2008-04-08 12 -272 272 2008-04-08 12 -272 272 2008-04-09 11 -272 272 2008-04-09 11 -272 272 2008-04-09 12 -272 272 2008-04-09 12 -273 273 2008-04-08 11 -273 273 2008-04-08 11 -273 273 2008-04-08 11 -273 273 2008-04-08 12 -273 273 2008-04-08 12 -273 273 2008-04-08 12 -273 273 2008-04-09 11 -273 273 2008-04-09 11 -273 273 2008-04-09 11 -273 273 2008-04-09 12 -273 273 2008-04-09 12 -273 273 2008-04-09 12 -274 274 2008-04-08 11 -274 274 2008-04-08 12 -274 274 2008-04-09 11 -274 274 2008-04-09 12 -275 275 2008-04-08 11 -275 275 2008-04-08 12 -275 275 2008-04-09 11 -275 275 2008-04-09 12 -277 277 2008-04-08 11 -277 277 2008-04-08 11 -277 277 2008-04-08 11 -277 277 2008-04-08 11 -277 277 2008-04-08 12 -277 277 2008-04-08 12 -277 277 2008-04-08 12 -277 277 2008-04-08 12 -277 277 2008-04-09 11 -277 277 2008-04-09 11 -277 277 2008-04-09 11 -277 277 2008-04-09 11 -277 277 2008-04-09 12 -277 277 2008-04-09 12 -277 277 2008-04-09 12 -277 277 2008-04-09 12 -278 278 2008-04-08 11 -278 278 2008-04-08 11 -278 278 2008-04-08 12 -278 278 2008-04-08 12 -278 278 2008-04-09 11 -278 278 2008-04-09 11 -278 278 2008-04-09 12 -278 278 2008-04-09 12 -28 28 2008-04-08 11 -28 28 2008-04-08 12 -28 28 2008-04-09 11 -28 28 2008-04-09 12 -280 280 2008-04-08 11 -280 280 2008-04-08 11 -280 280 2008-04-08 12 -280 280 2008-04-08 12 -280 280 2008-04-09 11 -280 280 2008-04-09 11 -280 280 2008-04-09 12 -280 280 2008-04-09 12 -281 281 2008-04-08 11 -281 281 2008-04-08 11 -281 281 2008-04-08 12 -281 281 2008-04-08 12 -281 281 2008-04-09 11 -281 281 2008-04-09 11 -281 281 2008-04-09 12 -281 281 2008-04-09 12 -282 282 2008-04-08 11 -282 282 2008-04-08 11 -282 282 2008-04-08 12 -282 282 2008-04-08 12 -282 282 2008-04-09 11 -282 282 2008-04-09 11 -282 282 2008-04-09 12 -282 282 2008-04-09 12 -283 283 2008-04-08 11 -283 283 2008-04-08 12 -283 283 2008-04-09 11 -283 283 2008-04-09 12 -284 284 2008-04-08 11 -284 284 2008-04-08 12 -284 284 2008-04-09 11 -284 284 2008-04-09 12 -285 285 2008-04-08 11 -285 285 2008-04-08 12 -285 285 2008-04-09 11 -285 285 2008-04-09 12 -286 286 2008-04-08 11 -286 286 2008-04-08 12 -286 286 2008-04-09 11 -286 286 2008-04-09 12 -287 287 2008-04-08 11 -287 287 2008-04-08 12 -287 287 2008-04-09 11 -287 287 2008-04-09 12 -288 288 2008-04-08 11 -288 288 2008-04-08 11 -288 288 2008-04-08 12 -288 288 2008-04-08 12 -288 288 2008-04-09 11 -288 288 2008-04-09 11 -288 288 2008-04-09 12 -288 288 2008-04-09 12 -289 289 2008-04-08 11 -289 289 2008-04-08 12 -289 289 2008-04-09 11 -289 289 2008-04-09 12 -291 291 2008-04-08 11 -291 291 2008-04-08 12 -291 291 2008-04-09 11 -291 291 2008-04-09 12 -292 292 2008-04-08 11 -292 292 2008-04-08 12 -292 292 2008-04-09 11 -292 292 2008-04-09 12 -296 296 2008-04-08 11 -296 296 2008-04-08 12 -296 296 2008-04-09 11 -296 296 2008-04-09 12 -298 298 2008-04-08 11 -298 298 2008-04-08 11 -298 298 2008-04-08 11 -298 298 2008-04-08 12 -298 298 2008-04-08 12 -298 298 2008-04-08 12 -298 298 2008-04-09 11 -298 298 2008-04-09 11 -298 298 2008-04-09 11 -298 298 2008-04-09 12 -298 298 2008-04-09 12 -298 298 2008-04-09 12 -30 30 2008-04-08 11 -30 30 2008-04-08 12 -30 30 2008-04-09 11 -30 30 2008-04-09 12 -302 302 2008-04-08 11 -302 302 2008-04-08 12 -302 302 2008-04-09 11 -302 302 2008-04-09 12 -305 305 2008-04-08 11 -305 305 2008-04-08 12 -305 305 2008-04-09 11 -305 305 2008-04-09 12 -306 306 2008-04-08 11 -306 306 2008-04-08 12 -306 306 2008-04-09 11 -306 306 2008-04-09 12 -307 307 2008-04-08 11 -307 307 2008-04-08 11 -307 307 2008-04-08 12 -307 307 2008-04-08 12 -307 307 2008-04-09 11 -307 307 2008-04-09 11 -307 307 2008-04-09 12 -307 307 2008-04-09 12 -308 308 2008-04-08 11 -308 308 2008-04-08 12 -308 308 2008-04-09 11 -308 308 2008-04-09 12 -309 309 2008-04-08 11 -309 309 2008-04-08 11 -309 309 2008-04-08 12 -309 309 2008-04-08 12 -309 309 2008-04-09 11 -309 309 2008-04-09 11 -309 309 2008-04-09 12 -309 309 2008-04-09 12 -310 310 2008-04-08 11 -310 310 2008-04-08 12 -310 310 2008-04-09 11 -310 310 2008-04-09 12 -311 311 2008-04-08 11 -311 311 2008-04-08 11 -311 311 2008-04-08 11 -311 311 2008-04-08 12 -311 311 2008-04-08 12 -311 311 2008-04-08 12 -311 311 2008-04-09 11 -311 311 2008-04-09 11 -311 311 2008-04-09 11 -311 311 2008-04-09 12 -311 311 2008-04-09 12 -311 311 2008-04-09 12 -315 315 2008-04-08 11 -315 315 2008-04-08 12 -315 315 2008-04-09 11 -315 315 2008-04-09 12 -316 316 2008-04-08 11 -316 316 2008-04-08 11 -316 316 2008-04-08 11 -316 316 2008-04-08 12 -316 316 2008-04-08 12 -316 316 2008-04-08 12 -316 316 2008-04-09 11 -316 316 2008-04-09 11 -316 316 2008-04-09 11 -316 316 2008-04-09 12 -316 316 2008-04-09 12 -316 316 2008-04-09 12 -317 317 2008-04-08 11 -317 317 2008-04-08 11 -317 317 2008-04-08 12 -317 317 2008-04-08 12 -317 317 2008-04-09 11 -317 317 2008-04-09 11 -317 317 2008-04-09 12 -317 317 2008-04-09 12 -318 318 2008-04-08 11 -318 318 2008-04-08 11 -318 318 2008-04-08 11 -318 318 2008-04-08 12 -318 318 2008-04-08 12 -318 318 2008-04-08 12 -318 318 2008-04-09 11 -318 318 2008-04-09 11 -318 318 2008-04-09 11 -318 318 2008-04-09 12 -318 318 2008-04-09 12 -318 318 2008-04-09 12 -321 321 2008-04-08 11 -321 321 2008-04-08 11 -321 321 2008-04-08 12 -321 321 2008-04-08 12 -321 321 2008-04-09 11 -321 321 2008-04-09 11 -321 321 2008-04-09 12 -321 321 2008-04-09 12 -322 322 2008-04-08 11 -322 322 2008-04-08 11 -322 322 2008-04-08 12 -322 322 2008-04-08 12 -322 322 2008-04-09 11 -322 322 2008-04-09 11 -322 322 2008-04-09 12 -322 322 2008-04-09 12 -323 323 2008-04-08 11 -323 323 2008-04-08 12 -323 323 2008-04-09 11 -323 323 2008-04-09 12 -325 325 2008-04-08 11 -325 325 2008-04-08 11 -325 325 2008-04-08 12 -325 325 2008-04-08 12 -325 325 2008-04-09 11 -325 325 2008-04-09 11 -325 325 2008-04-09 12 -325 325 2008-04-09 12 -327 327 2008-04-08 11 -327 327 2008-04-08 11 -327 327 2008-04-08 11 -327 327 2008-04-08 12 -327 327 2008-04-08 12 -327 327 2008-04-08 12 -327 327 2008-04-09 11 -327 327 2008-04-09 11 -327 327 2008-04-09 11 -327 327 2008-04-09 12 -327 327 2008-04-09 12 -327 327 2008-04-09 12 -33 33 2008-04-08 11 -33 33 2008-04-08 12 -33 33 2008-04-09 11 -33 33 2008-04-09 12 -331 331 2008-04-08 11 -331 331 2008-04-08 11 -331 331 2008-04-08 12 -331 331 2008-04-08 12 -331 331 2008-04-09 11 -331 331 2008-04-09 11 -331 331 2008-04-09 12 -331 331 2008-04-09 12 -332 332 2008-04-08 11 -332 332 2008-04-08 12 -332 332 2008-04-09 11 -332 332 2008-04-09 12 -333 333 2008-04-08 11 -333 333 2008-04-08 11 -333 333 2008-04-08 12 -333 333 2008-04-08 12 -333 333 2008-04-09 11 -333 333 2008-04-09 11 -333 333 2008-04-09 12 -333 333 2008-04-09 12 -335 335 2008-04-08 11 -335 335 2008-04-08 12 -335 335 2008-04-09 11 -335 335 2008-04-09 12 -336 336 2008-04-08 11 -336 336 2008-04-08 12 -336 336 2008-04-09 11 -336 336 2008-04-09 12 -338 338 2008-04-08 11 -338 338 2008-04-08 12 -338 338 2008-04-09 11 -338 338 2008-04-09 12 -339 339 2008-04-08 11 -339 339 2008-04-08 12 -339 339 2008-04-09 11 -339 339 2008-04-09 12 -34 34 2008-04-08 11 -34 34 2008-04-08 12 -34 34 2008-04-09 11 -34 34 2008-04-09 12 -341 341 2008-04-08 11 -341 341 2008-04-08 12 -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 410 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Offset of rows: 400 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 400,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -189 189 2008-04-08 11 -189 189 2008-04-08 12 -189 189 2008-04-09 11 -189 189 2008-04-09 12 -19 19 2008-04-08 11 -19 19 2008-04-08 12 -19 19 2008-04-09 11 -19 19 2008-04-09 12 -190 190 2008-04-08 11 -190 190 2008-04-08 12 -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 500 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Offset of rows: 490 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 5410 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -201 201 2008-04-09 11 -201 201 2008-04-09 12 -202 202 2008-04-08 11 -202 202 2008-04-08 12 -202 202 2008-04-09 11 -202 202 2008-04-09 12 -203 203 2008-04-08 11 -203 203 2008-04-08 11 -203 203 2008-04-08 12 -203 203 2008-04-08 12 -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 510 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Offset of rows: 490 - Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 10820 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -201 201 2008-04-09 11 -201 201 2008-04-09 12 -202 202 2008-04-08 11 -202 202 2008-04-08 12 -202 202 2008-04-09 11 -202 202 2008-04-09 12 -203 203 2008-04-08 11 -203 203 2008-04-08 11 -203 203 2008-04-08 12 -203 203 2008-04-08 12 -203 203 2008-04-09 11 -203 203 2008-04-09 11 -203 203 2008-04-09 12 -203 203 2008-04-09 12 -205 205 2008-04-08 11 -205 205 2008-04-08 11 -205 205 2008-04-08 12 -205 205 2008-04-08 12 -205 205 2008-04-09 11 -205 205 2008-04-09 11 -PREHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), substr(value, 5) (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 1090 - TopN Hash Memory Usage: 0.1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1082000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 600 - Offset of rows: 490 - Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 600 Data size: 324600 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 600 - Processor Tree: - ListSink - -PREHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT srcpart.key, substr(srcpart.value,5) as csubstr, ds, hr FROM srcpart ORDER BY srcpart.key, csubstr, ds, hr LIMIT 490,600 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -201 201 2008-04-09 11 -201 201 2008-04-09 12 -202 202 2008-04-08 11 -202 202 2008-04-08 12 -202 202 2008-04-09 11 -202 202 2008-04-09 12 -203 203 2008-04-08 11 -203 203 2008-04-08 11 -203 203 2008-04-08 12 -203 203 2008-04-08 12 -203 203 2008-04-09 11 -203 203 2008-04-09 11 -203 203 2008-04-09 12 -203 203 2008-04-09 12 -205 205 2008-04-08 11 -205 205 2008-04-08 11 -205 205 2008-04-08 12 -205 205 2008-04-08 12 -205 205 2008-04-09 11 -205 205 2008-04-09 11 -205 205 2008-04-09 12 -205 205 2008-04-09 12 -207 207 2008-04-08 11 -207 207 2008-04-08 11 -207 207 2008-04-08 12 -207 207 2008-04-08 12 -207 207 2008-04-09 11 -207 207 2008-04-09 11 -207 207 2008-04-09 12 -207 207 2008-04-09 12 -208 208 2008-04-08 11 -208 208 2008-04-08 11 -208 208 2008-04-08 11 -208 208 2008-04-08 12 -208 208 2008-04-08 12 -208 208 2008-04-08 12 -208 208 2008-04-09 11 -208 208 2008-04-09 11 -208 208 2008-04-09 11 -208 208 2008-04-09 12 -208 208 2008-04-09 12 -208 208 2008-04-09 12 -209 209 2008-04-08 11 -209 209 2008-04-08 11 -209 209 2008-04-08 12 -209 209 2008-04-08 12 -209 209 2008-04-09 11 -209 209 2008-04-09 11 -209 209 2008-04-09 12 -209 209 2008-04-09 12 -213 213 2008-04-08 11 -213 213 2008-04-08 11 -213 213 2008-04-08 12 -213 213 2008-04-08 12 -213 213 2008-04-09 11 -213 213 2008-04-09 11 -213 213 2008-04-09 12 -213 213 2008-04-09 12 -214 214 2008-04-08 11 -214 214 2008-04-08 12 -214 214 2008-04-09 11 -214 214 2008-04-09 12 -216 216 2008-04-08 11 -216 216 2008-04-08 11 -216 216 2008-04-08 12 -216 216 2008-04-08 12 -216 216 2008-04-09 11 -216 216 2008-04-09 11 -216 216 2008-04-09 12 -216 216 2008-04-09 12 -217 217 2008-04-08 11 -217 217 2008-04-08 11 -217 217 2008-04-08 12 -217 217 2008-04-08 12 -217 217 2008-04-09 11 -217 217 2008-04-09 11 -217 217 2008-04-09 12 -217 217 2008-04-09 12 -218 218 2008-04-08 11 -218 218 2008-04-08 12 -218 218 2008-04-09 11 -218 218 2008-04-09 12 -219 219 2008-04-08 11 -219 219 2008-04-08 11 -219 219 2008-04-08 12 -219 219 2008-04-08 12 -219 219 2008-04-09 11 -219 219 2008-04-09 11 -219 219 2008-04-09 12 -219 219 2008-04-09 12 -221 221 2008-04-08 11 -221 221 2008-04-08 11 -221 221 2008-04-08 12 -221 221 2008-04-08 12 -221 221 2008-04-09 11 -221 221 2008-04-09 11 -221 221 2008-04-09 12 -221 221 2008-04-09 12 -222 222 2008-04-08 11 -222 222 2008-04-08 12 -222 222 2008-04-09 11 -222 222 2008-04-09 12 -223 223 2008-04-08 11 -223 223 2008-04-08 11 -223 223 2008-04-08 12 -223 223 2008-04-08 12 -223 223 2008-04-09 11 -223 223 2008-04-09 11 -223 223 2008-04-09 12 -223 223 2008-04-09 12 -224 224 2008-04-08 11 -224 224 2008-04-08 11 -224 224 2008-04-08 12 -224 224 2008-04-08 12 -224 224 2008-04-09 11 -224 224 2008-04-09 11 -224 224 2008-04-09 12 -224 224 2008-04-09 12 -226 226 2008-04-08 11 -226 226 2008-04-08 12 -226 226 2008-04-09 11 -226 226 2008-04-09 12 -228 228 2008-04-08 11 -228 228 2008-04-08 12 -228 228 2008-04-09 11 -228 228 2008-04-09 12 -229 229 2008-04-08 11 -229 229 2008-04-08 11 -229 229 2008-04-08 12 -229 229 2008-04-08 12 -229 229 2008-04-09 11 -229 229 2008-04-09 11 -229 229 2008-04-09 12 -229 229 2008-04-09 12 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 11 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-08 12 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 11 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -230 230 2008-04-09 12 -233 233 2008-04-08 11 -233 233 2008-04-08 11 -233 233 2008-04-08 12 -233 233 2008-04-08 12 -233 233 2008-04-09 11 -233 233 2008-04-09 11 -233 233 2008-04-09 12 -233 233 2008-04-09 12 -235 235 2008-04-08 11 -235 235 2008-04-08 12 -235 235 2008-04-09 11 -235 235 2008-04-09 12 -237 237 2008-04-08 11 -237 237 2008-04-08 11 -237 237 2008-04-08 12 -237 237 2008-04-08 12 -237 237 2008-04-09 11 -237 237 2008-04-09 11 -237 237 2008-04-09 12 -237 237 2008-04-09 12 -238 238 2008-04-08 11 -238 238 2008-04-08 11 -238 238 2008-04-08 12 -238 238 2008-04-08 12 -238 238 2008-04-09 11 -238 238 2008-04-09 11 -238 238 2008-04-09 12 -238 238 2008-04-09 12 -239 239 2008-04-08 11 -239 239 2008-04-08 11 -239 239 2008-04-08 12 -239 239 2008-04-08 12 -239 239 2008-04-09 11 -239 239 2008-04-09 11 -239 239 2008-04-09 12 -239 239 2008-04-09 12 -24 24 2008-04-08 11 -24 24 2008-04-08 11 -24 24 2008-04-08 12 -24 24 2008-04-08 12 -24 24 2008-04-09 11 -24 24 2008-04-09 11 -24 24 2008-04-09 12 -24 24 2008-04-09 12 -241 241 2008-04-08 11 -241 241 2008-04-08 12 -241 241 2008-04-09 11 -241 241 2008-04-09 12 -242 242 2008-04-08 11 -242 242 2008-04-08 11 -242 242 2008-04-08 12 -242 242 2008-04-08 12 -242 242 2008-04-09 11 -242 242 2008-04-09 11 -242 242 2008-04-09 12 -242 242 2008-04-09 12 -244 244 2008-04-08 11 -244 244 2008-04-08 12 -244 244 2008-04-09 11 -244 244 2008-04-09 12 -247 247 2008-04-08 11 -247 247 2008-04-08 12 -247 247 2008-04-09 11 -247 247 2008-04-09 12 -248 248 2008-04-08 11 -248 248 2008-04-08 12 -248 248 2008-04-09 11 -248 248 2008-04-09 12 -249 249 2008-04-08 11 -249 249 2008-04-08 12 -249 249 2008-04-09 11 -249 249 2008-04-09 12 -252 252 2008-04-08 11 -252 252 2008-04-08 12 -252 252 2008-04-09 11 -252 252 2008-04-09 12 -255 255 2008-04-08 11 -255 255 2008-04-08 11 -255 255 2008-04-08 12 -255 255 2008-04-08 12 -255 255 2008-04-09 11 -255 255 2008-04-09 11 -255 255 2008-04-09 12 -255 255 2008-04-09 12 -256 256 2008-04-08 11 -256 256 2008-04-08 11 -256 256 2008-04-08 12 -256 256 2008-04-08 12 -256 256 2008-04-09 11 -256 256 2008-04-09 11 -256 256 2008-04-09 12 -256 256 2008-04-09 12 -257 257 2008-04-08 11 -257 257 2008-04-08 12 -257 257 2008-04-09 11 -257 257 2008-04-09 12 -258 258 2008-04-08 11 -258 258 2008-04-08 12 -258 258 2008-04-09 11 -258 258 2008-04-09 12 -26 26 2008-04-08 11 -26 26 2008-04-08 11 -26 26 2008-04-08 12 -26 26 2008-04-08 12 -26 26 2008-04-09 11 -26 26 2008-04-09 11 -26 26 2008-04-09 12 -26 26 2008-04-09 12 -260 260 2008-04-08 11 -260 260 2008-04-08 12 -260 260 2008-04-09 11 -260 260 2008-04-09 12 -262 262 2008-04-08 11 -262 262 2008-04-08 12 -262 262 2008-04-09 11 -262 262 2008-04-09 12 -263 263 2008-04-08 11 -263 263 2008-04-08 12 -263 263 2008-04-09 11 -263 263 2008-04-09 12 -265 265 2008-04-08 11 -265 265 2008-04-08 11 -265 265 2008-04-08 12 -265 265 2008-04-08 12 -265 265 2008-04-09 11 -265 265 2008-04-09 11 -265 265 2008-04-09 12 -265 265 2008-04-09 12 -266 266 2008-04-08 11 -266 266 2008-04-08 12 -266 266 2008-04-09 11 -266 266 2008-04-09 12 -27 27 2008-04-08 11 -27 27 2008-04-08 12 -27 27 2008-04-09 11 -27 27 2008-04-09 12 -272 272 2008-04-08 11 -272 272 2008-04-08 11 -272 272 2008-04-08 12 -272 272 2008-04-08 12 -272 272 2008-04-09 11 -272 272 2008-04-09 11 -272 272 2008-04-09 12 -272 272 2008-04-09 12 -273 273 2008-04-08 11 -273 273 2008-04-08 11 -273 273 2008-04-08 11 -273 273 2008-04-08 12 -273 273 2008-04-08 12 -273 273 2008-04-08 12 -273 273 2008-04-09 11 -273 273 2008-04-09 11 -273 273 2008-04-09 11 -273 273 2008-04-09 12 -273 273 2008-04-09 12 -273 273 2008-04-09 12 -274 274 2008-04-08 11 -274 274 2008-04-08 12 -274 274 2008-04-09 11 -274 274 2008-04-09 12 -275 275 2008-04-08 11 -275 275 2008-04-08 12 -275 275 2008-04-09 11 -275 275 2008-04-09 12 -277 277 2008-04-08 11 -277 277 2008-04-08 11 -277 277 2008-04-08 11 -277 277 2008-04-08 11 -277 277 2008-04-08 12 -277 277 2008-04-08 12 -277 277 2008-04-08 12 -277 277 2008-04-08 12 -277 277 2008-04-09 11 -277 277 2008-04-09 11 -277 277 2008-04-09 11 -277 277 2008-04-09 11 -277 277 2008-04-09 12 -277 277 2008-04-09 12 -277 277 2008-04-09 12 -277 277 2008-04-09 12 -278 278 2008-04-08 11 -278 278 2008-04-08 11 -278 278 2008-04-08 12 -278 278 2008-04-08 12 -278 278 2008-04-09 11 -278 278 2008-04-09 11 -278 278 2008-04-09 12 -278 278 2008-04-09 12 -28 28 2008-04-08 11 -28 28 2008-04-08 12 -28 28 2008-04-09 11 -28 28 2008-04-09 12 -280 280 2008-04-08 11 -280 280 2008-04-08 11 -280 280 2008-04-08 12 -280 280 2008-04-08 12 -280 280 2008-04-09 11 -280 280 2008-04-09 11 -280 280 2008-04-09 12 -280 280 2008-04-09 12 -281 281 2008-04-08 11 -281 281 2008-04-08 11 -281 281 2008-04-08 12 -281 281 2008-04-08 12 -281 281 2008-04-09 11 -281 281 2008-04-09 11 -281 281 2008-04-09 12 -281 281 2008-04-09 12 -282 282 2008-04-08 11 -282 282 2008-04-08 11 -282 282 2008-04-08 12 -282 282 2008-04-08 12 -282 282 2008-04-09 11 -282 282 2008-04-09 11 -282 282 2008-04-09 12 -282 282 2008-04-09 12 -283 283 2008-04-08 11 -283 283 2008-04-08 12 -283 283 2008-04-09 11 -283 283 2008-04-09 12 -284 284 2008-04-08 11 -284 284 2008-04-08 12 -284 284 2008-04-09 11 -284 284 2008-04-09 12 -285 285 2008-04-08 11 -285 285 2008-04-08 12 -285 285 2008-04-09 11 -285 285 2008-04-09 12 -286 286 2008-04-08 11 -286 286 2008-04-08 12 -286 286 2008-04-09 11 -286 286 2008-04-09 12 -287 287 2008-04-08 11 -287 287 2008-04-08 12 -287 287 2008-04-09 11 -287 287 2008-04-09 12 -288 288 2008-04-08 11 -288 288 2008-04-08 11 -288 288 2008-04-08 12 -288 288 2008-04-08 12 -288 288 2008-04-09 11 -288 288 2008-04-09 11 -288 288 2008-04-09 12 -288 288 2008-04-09 12 -289 289 2008-04-08 11 -289 289 2008-04-08 12 -289 289 2008-04-09 11 -289 289 2008-04-09 12 -291 291 2008-04-08 11 -291 291 2008-04-08 12 -291 291 2008-04-09 11 -291 291 2008-04-09 12 -292 292 2008-04-08 11 -292 292 2008-04-08 12 -292 292 2008-04-09 11 -292 292 2008-04-09 12 -296 296 2008-04-08 11 -296 296 2008-04-08 12 -296 296 2008-04-09 11 -296 296 2008-04-09 12 -298 298 2008-04-08 11 -298 298 2008-04-08 11 -298 298 2008-04-08 11 -298 298 2008-04-08 12 -298 298 2008-04-08 12 -298 298 2008-04-08 12 -298 298 2008-04-09 11 -298 298 2008-04-09 11 -298 298 2008-04-09 11 -298 298 2008-04-09 12 -298 298 2008-04-09 12 -298 298 2008-04-09 12 -30 30 2008-04-08 11 -30 30 2008-04-08 12 -30 30 2008-04-09 11 -30 30 2008-04-09 12 -302 302 2008-04-08 11 -302 302 2008-04-08 12 -302 302 2008-04-09 11 -302 302 2008-04-09 12 -305 305 2008-04-08 11 -305 305 2008-04-08 12 -305 305 2008-04-09 11 -305 305 2008-04-09 12 -306 306 2008-04-08 11 -306 306 2008-04-08 12 -306 306 2008-04-09 11 -306 306 2008-04-09 12 -307 307 2008-04-08 11 -307 307 2008-04-08 11 -307 307 2008-04-08 12 -307 307 2008-04-08 12 -307 307 2008-04-09 11 -307 307 2008-04-09 11 -307 307 2008-04-09 12 -307 307 2008-04-09 12 -308 308 2008-04-08 11 -308 308 2008-04-08 12 -308 308 2008-04-09 11 -308 308 2008-04-09 12 -309 309 2008-04-08 11 -309 309 2008-04-08 11 -309 309 2008-04-08 12 -309 309 2008-04-08 12 -309 309 2008-04-09 11 -309 309 2008-04-09 11 -309 309 2008-04-09 12 -309 309 2008-04-09 12 -310 310 2008-04-08 11 -310 310 2008-04-08 12 -310 310 2008-04-09 11 -310 310 2008-04-09 12 -311 311 2008-04-08 11 -311 311 2008-04-08 11 -311 311 2008-04-08 11 -311 311 2008-04-08 12 -311 311 2008-04-08 12 -311 311 2008-04-08 12 -311 311 2008-04-09 11 -311 311 2008-04-09 11 -311 311 2008-04-09 11 -311 311 2008-04-09 12 -311 311 2008-04-09 12 -311 311 2008-04-09 12 -315 315 2008-04-08 11 -315 315 2008-04-08 12 -315 315 2008-04-09 11 -315 315 2008-04-09 12 -316 316 2008-04-08 11 -316 316 2008-04-08 11 -316 316 2008-04-08 11 -316 316 2008-04-08 12 -316 316 2008-04-08 12 -316 316 2008-04-08 12 -316 316 2008-04-09 11 -316 316 2008-04-09 11 -316 316 2008-04-09 11 -316 316 2008-04-09 12 -316 316 2008-04-09 12 -316 316 2008-04-09 12 -317 317 2008-04-08 11 -317 317 2008-04-08 11 -317 317 2008-04-08 12 -317 317 2008-04-08 12 -317 317 2008-04-09 11 -317 317 2008-04-09 11 -317 317 2008-04-09 12 -317 317 2008-04-09 12 -318 318 2008-04-08 11 -318 318 2008-04-08 11 -318 318 2008-04-08 11 -318 318 2008-04-08 12 -318 318 2008-04-08 12 -318 318 2008-04-08 12 -318 318 2008-04-09 11 -318 318 2008-04-09 11 -318 318 2008-04-09 11 -318 318 2008-04-09 12 -318 318 2008-04-09 12 -318 318 2008-04-09 12 -321 321 2008-04-08 11 -321 321 2008-04-08 11 -321 321 2008-04-08 12 -321 321 2008-04-08 12 -321 321 2008-04-09 11 -321 321 2008-04-09 11 -321 321 2008-04-09 12 -321 321 2008-04-09 12 -322 322 2008-04-08 11 -322 322 2008-04-08 11 -322 322 2008-04-08 12 -322 322 2008-04-08 12 -322 322 2008-04-09 11 -322 322 2008-04-09 11 -322 322 2008-04-09 12 -322 322 2008-04-09 12 -323 323 2008-04-08 11 -323 323 2008-04-08 12 -323 323 2008-04-09 11 -323 323 2008-04-09 12 -325 325 2008-04-08 11 -325 325 2008-04-08 11 -325 325 2008-04-08 12 -325 325 2008-04-08 12 -325 325 2008-04-09 11 -325 325 2008-04-09 11 -325 325 2008-04-09 12 -325 325 2008-04-09 12 -327 327 2008-04-08 11 -327 327 2008-04-08 11 -327 327 2008-04-08 11 -327 327 2008-04-08 12 -327 327 2008-04-08 12 -327 327 2008-04-08 12 -327 327 2008-04-09 11 -327 327 2008-04-09 11 -327 327 2008-04-09 11 -327 327 2008-04-09 12 -327 327 2008-04-09 12 -327 327 2008-04-09 12 -33 33 2008-04-08 11 -33 33 2008-04-08 12 -33 33 2008-04-09 11 -33 33 2008-04-09 12 -331 331 2008-04-08 11 -331 331 2008-04-08 11 -331 331 2008-04-08 12 -331 331 2008-04-08 12 -331 331 2008-04-09 11 -331 331 2008-04-09 11 -331 331 2008-04-09 12 -331 331 2008-04-09 12 -332 332 2008-04-08 11 -332 332 2008-04-08 12 -332 332 2008-04-09 11 -332 332 2008-04-09 12 -333 333 2008-04-08 11 -333 333 2008-04-08 11 -333 333 2008-04-08 12 -333 333 2008-04-08 12 -333 333 2008-04-09 11 -333 333 2008-04-09 11 -333 333 2008-04-09 12 -333 333 2008-04-09 12 -335 335 2008-04-08 11 -335 335 2008-04-08 12 -335 335 2008-04-09 11 -335 335 2008-04-09 12 -336 336 2008-04-08 11 -336 336 2008-04-08 12 -336 336 2008-04-09 11 -336 336 2008-04-09 12 -338 338 2008-04-08 11 -338 338 2008-04-08 12 -338 338 2008-04-09 11 -338 338 2008-04-09 12 -339 339 2008-04-08 11 -339 339 2008-04-08 12 -339 339 2008-04-09 11 -339 339 2008-04-09 12 -34 34 2008-04-08 11 -34 34 2008-04-08 12 -34 34 2008-04-09 11 -34 34 2008-04-09 12 -341 341 2008-04-08 11 -341 341 2008-04-08 12 diff --git ql/src/test/results/clientpositive/optional_outer.q.out ql/src/test/results/clientpositive/optional_outer.q.out deleted file mode 100644 index e8ad342a22..0000000000 --- ql/src/test/results/clientpositive/optional_outer.q.out +++ /dev/null @@ -1,418 +0,0 @@ -PREHOOK: query: EXPLAIN SELECT * FROM src a LEFT OUTER JOIN src b on (a.key=b.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src a LEFT OUTER JOIN src b on (a.key=b.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN SELECT * FROM src a LEFT JOIN src b on (a.key=b.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src a LEFT JOIN src b on (a.key=b.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN SELECT * FROM src a RIGHT OUTER JOIN src b on (a.key=b.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src a RIGHT OUTER JOIN src b on (a.key=b.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN SELECT * FROM src a RIGHT JOIN src b on (a.key=b.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src a RIGHT JOIN src b on (a.key=b.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN SELECT * FROM src a FULL OUTER JOIN src b on (a.key=b.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src a FULL OUTER JOIN src b on (a.key=b.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN SELECT * FROM src a FULL JOIN src b on (a.key=b.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src a FULL JOIN src b on (a.key=b.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/orc_avro_partition_uniontype.q.out ql/src/test/results/clientpositive/orc_avro_partition_uniontype.q.out deleted file mode 100644 index da8d9cc356..0000000000 --- ql/src/test/results/clientpositive/orc_avro_partition_uniontype.q.out +++ /dev/null @@ -1,40 +0,0 @@ -PREHOOK: query: CREATE TABLE avro_orc_partitioned_uniontype (a uniontype) PARTITIONED BY (b int) STORED AS ORC -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@avro_orc_partitioned_uniontype -POSTHOOK: query: CREATE TABLE avro_orc_partitioned_uniontype (a uniontype) PARTITIONED BY (b int) STORED AS ORC -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@avro_orc_partitioned_uniontype -PREHOOK: query: INSERT INTO avro_orc_partitioned_uniontype PARTITION (b=1) SELECT create_union(1, true, value) FROM src LIMIT 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@avro_orc_partitioned_uniontype@b=1 -POSTHOOK: query: INSERT INTO avro_orc_partitioned_uniontype PARTITION (b=1) SELECT create_union(1, true, value) FROM src LIMIT 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@avro_orc_partitioned_uniontype@b=1 -POSTHOOK: Lineage: avro_orc_partitioned_uniontype PARTITION(b=1).a EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: ALTER TABLE avro_orc_partitioned_uniontype SET FILEFORMAT AVRO -PREHOOK: type: ALTERTABLE_FILEFORMAT -PREHOOK: Input: default@avro_orc_partitioned_uniontype -PREHOOK: Output: default@avro_orc_partitioned_uniontype -POSTHOOK: query: ALTER TABLE avro_orc_partitioned_uniontype SET FILEFORMAT AVRO -POSTHOOK: type: ALTERTABLE_FILEFORMAT -POSTHOOK: Input: default@avro_orc_partitioned_uniontype -POSTHOOK: Output: default@avro_orc_partitioned_uniontype -PREHOOK: query: SELECT * FROM avro_orc_partitioned_uniontype -PREHOOK: type: QUERY -PREHOOK: Input: default@avro_orc_partitioned_uniontype -PREHOOK: Input: default@avro_orc_partitioned_uniontype@b=1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM avro_orc_partitioned_uniontype -POSTHOOK: type: QUERY -POSTHOOK: Input: default@avro_orc_partitioned_uniontype -POSTHOOK: Input: default@avro_orc_partitioned_uniontype@b=1 -#### A masked pattern was here #### -{1:"val_165"} 1 -{1:"val_27"} 1 -{1:"val_311"} 1 -{1:"val_86"} 1 -{1:"val_238"} 1 diff --git ql/src/test/results/clientpositive/orc_nested_column_pruning.q.out ql/src/test/results/clientpositive/orc_nested_column_pruning.q.out deleted file mode 100644 index 029eb17b08..0000000000 --- ql/src/test/results/clientpositive/orc_nested_column_pruning.q.out +++ /dev/null @@ -1,1999 +0,0 @@ -PREHOOK: query: DROP TABLE IF EXISTS dummy_n4 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS dummy_n4 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE dummy_n4 (i int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dummy_n4 -POSTHOOK: query: CREATE TABLE dummy_n4 (i int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dummy_n4 -PREHOOK: query: INSERT INTO TABLE dummy_n4 VALUES (42) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@dummy_n4 -POSTHOOK: query: INSERT INTO TABLE dummy_n4 VALUES (42) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@dummy_n4 -POSTHOOK: Lineage: dummy_n4.i SCRIPT [] -PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_1_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE nested_tbl_1_n0 ( - a int, - s1 struct, f6: int>, - s2 struct, f11: map>>, - s3 struct>>, - s4 map>, - s5 struct>>>, - s6 map>>>> -) STORED AS ORC -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@nested_tbl_1_n0 -POSTHOOK: query: CREATE TABLE nested_tbl_1_n0 ( - a int, - s1 struct, f6: int>, - s2 struct, f11: map>>, - s3 struct>>, - s4 map>, - s5 struct>>>, - s6 map>>>> -) STORED AS ORC -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nested_tbl_1_n0 -PREHOOK: query: INSERT INTO TABLE nested_tbl_1_n0 SELECT - 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), - named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), - named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), - map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), - named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), - map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), - 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) -FROM dummy_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@dummy_n4 -PREHOOK: Output: default@nested_tbl_1_n0 -POSTHOOK: query: INSERT INTO TABLE nested_tbl_1_n0 SELECT - 1, named_struct('f1', false, 'f2', 'foo', 'f3', named_struct('f4', 4, 'f5', cast(5.0 as double)), 'f6', 4), - named_struct('f7', 'f7', 'f8', named_struct('f9', true, 'f10', array(10, 11), 'f11', map('key1', true, 'key2', false))), - named_struct('f12', array(named_struct('f13', 'foo', 'f14', 14), named_struct('f13', 'bar', 'f14', 28))), - map('key1', named_struct('f15', 1), 'key2', named_struct('f15', 2)), - named_struct('f16', array(named_struct('f17', 'foo', 'f18', named_struct('f19', 14)), named_struct('f17', 'bar', 'f18', named_struct('f19', 28)))), - map('key1', named_struct('f20', array(named_struct('f21', named_struct('f22', 1)))), - 'key2', named_struct('f20', array(named_struct('f21', named_struct('f22', 2))))) -FROM dummy_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dummy_n4 -POSTHOOK: Output: default@nested_tbl_1_n0 -POSTHOOK: Lineage: nested_tbl_1_n0.a SIMPLE [] -POSTHOOK: Lineage: nested_tbl_1_n0.s1 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n0.s2 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n0.s3 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n0.s4 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n0.s5 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_1_n0.s6 EXPRESSION [] -PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_2_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE nested_tbl_2_n0 LIKE nested_tbl_1_n0 -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@nested_tbl_2_n0 -POSTHOOK: query: CREATE TABLE nested_tbl_2_n0 LIKE nested_tbl_1_n0 -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nested_tbl_2_n0 -PREHOOK: query: INSERT INTO TABLE nested_tbl_2_n0 SELECT - 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), - named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), - named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), - map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), - named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), - map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), - 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) -FROM dummy_n4 -PREHOOK: type: QUERY -PREHOOK: Input: default@dummy_n4 -PREHOOK: Output: default@nested_tbl_2_n0 -POSTHOOK: query: INSERT INTO TABLE nested_tbl_2_n0 SELECT - 2, named_struct('f1', true, 'f2', 'bar', 'f3', named_struct('f4', 4, 'f5', cast(6.5 as double)), 'f6', 4), - named_struct('f7', 'f72', 'f8', named_struct('f9', false, 'f10', array(20, 22), 'f11', map('key3', true, 'key4', false))), - named_struct('f12', array(named_struct('f13', 'bar', 'f14', 28), named_struct('f13', 'foo', 'f14', 56))), - map('key3', named_struct('f15', 3), 'key4', named_struct('f15', 4)), - named_struct('f16', array(named_struct('f17', 'bar', 'f18', named_struct('f19', 28)), named_struct('f17', 'foo', 'f18', named_struct('f19', 56)))), - map('key3', named_struct('f20', array(named_struct('f21', named_struct('f22', 3)))), - 'key4', named_struct('f20', array(named_struct('f21', named_struct('f22', 4))))) -FROM dummy_n4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dummy_n4 -POSTHOOK: Output: default@nested_tbl_2_n0 -POSTHOOK: Lineage: nested_tbl_2_n0.a SIMPLE [] -POSTHOOK: Lineage: nested_tbl_2_n0.s1 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n0.s2 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n0.s3 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n0.s4 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n0.s5 EXPRESSION [] -POSTHOOK: Lineage: nested_tbl_2_n0.s6 EXPRESSION [] -PREHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT a FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: a (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -1 -PREHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f1 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f1 (type: boolean) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f1 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -false -PREHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f1, s1.f2 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f1 (type: boolean), s1.f2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f1, s1.f2 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -false foo -PREHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3, s1.f3.f4 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -{"f4":4,"f5":5.0} 4 -PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f3.f5 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -5.0 -PREHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f3.f4, s2.f8.f9 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f4 (type: int), s2.f8.f9 (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f4, s2.f8.f9 FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -4 true -PREHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - filterExpr: (not s1.f1) (type: boolean) - Pruned Column Paths: s1.f2, s1.f1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not s1.f1) (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f2 FROM nested_tbl_1_n0 WHERE s1.f1 = FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -foo -PREHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - filterExpr: (s1.f3.f4 = 4) (type: boolean) - Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f3.f4 = 4) (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f5 FROM nested_tbl_1_n0 WHERE s1.f3.f4 = 4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -5.0 -PREHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - filterExpr: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) - Pruned Column Paths: s1.f2, s2.f8 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((s1.f2 = 'foo') and (size(s2.f8.f10) > 1) and s2.f8.f11['key1']) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s2.f8 (type: struct,f11:map>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s2.f8 FROM nested_tbl_1_n0 WHERE s1.f2 = 'foo' AND size(s2.f8.f10) > 1 AND s2.f8.f11['key1'] = TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -{"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} -PREHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n0 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT col1, col2 FROM nested_tbl_1_n0 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s2.f8.f10 - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s3 (type: struct>>) - outputColumnNames: s3 - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int) - outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col3.f12 (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: s2.f8.f10 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 1 Data size: 3632 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col3, _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int) - outputColumnNames: _col10 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col3.f12 (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 2 Data size: 7264 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col10, _col11 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col10 (type: int), _col11 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 14528 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n0 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT col1, col2 FROM nested_tbl_1_n0 -LATERAL VIEW explode(s2.f8.f10) tbl1 AS col1 -LATERAL VIEW explode(s3.f12) tbl2 AS col2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -10 {"f13":"foo","f14":14} -10 {"f13":"bar","f14":28} -11 {"f13":"foo","f14":14} -11 {"f13":"bar","f14":28} -PREHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s2.f8.f10, s1.f3.f4 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (s2.f8.f10[1] pmod s1.f3.f4) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT pmod(s2.f8.f10[1], s1.f3.f4) FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -3 -PREHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f3.f5, s1.f3.f4 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3.f5 (type: double), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: double) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: double) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: double) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3.f5, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3.f5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -5.0 1 -PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: struct) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: struct) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: struct) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -{"f4":4,"f5":5.0} 1 -PREHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f3 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f3 (type: struct), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: struct) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: struct) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: struct) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: struct) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: struct) - null sort order: z - sort order: + - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s1.f3, count(s1.f3.f4) FROM nested_tbl_1_n0 GROUP BY s1.f3 ORDER BY s1.f3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -{"f4":4,"f5":5.0} 1 -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -PREHOOK: Input: default@nested_tbl_2_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -POSTHOOK: Input: default@nested_tbl_2_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f3.f4 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f6 is not null and (not s2.f8.f9)) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f6 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0.f3.f4 (type: int) - 1 _col0.f6 (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -PREHOOK: Input: default@nested_tbl_2_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_2_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == FALSE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -POSTHOOK: Input: default@nested_tbl_2_n0 -#### A masked pattern was here #### -5.0 {"f9":false,"f10":[20,22],"f11":{"key3":true,"key4":false}} -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f3.f4 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f3.f4 (type: int) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: (s1.f6 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f6 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s2 (type: struct,f11:map>>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0.f6 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0.f6 (type: int) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0.f3.f4 (type: int) - 1 _col0.f6 (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double), _col2.f8 (type: struct,f11:map>) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5, t2.s2.f8 -FROM nested_tbl_1_n0 t1 JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 -WHERE t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -5.0 {"f9":true,"f10":[10,11],"f11":{"key1":true,"key2":false}} -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), true (type: boolean) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: int), true (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) - Pruned Column Paths: s1.f6, s2.f8.f9 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (s1.f6 is not null and s2.f8.f9 is not null and s2.f8.f9) (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1.f6 (type: int), s2.f8.f9 (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int), _col1 (type: boolean) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: boolean) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int), true (type: boolean) - 1 _col0 (type: int), _col1 (type: boolean) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t2.s2.f8.f9 == TRUE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -5.0 -Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s2 (type: struct,f11:map>>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1152 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - residual filter predicates: {(_col0.f1 <> _col1.f8.f9)} - Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1469 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -5.0 -PREHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f3.f4 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s1.f3.f4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 316 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f6:int>) - TableScan - alias: t2 - filterExpr: s1.f6 is not null (type: boolean) - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: s1.f6 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s2 (type: struct,f11:map>>), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 1468 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: struct,f11:map>>) - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col0, _col2 - residual filter predicates: {(_col0.f1 <> _col2.f8.f9)} - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0.f3.f5 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 347 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t1.s1.f3.f5 -FROM nested_tbl_1_n0 t1 LEFT SEMI JOIN nested_tbl_1_n0 t2 -ON t1.s1.f3.f4 = t2.s1.f6 AND t1.s1.f1 <> t2.s2.f8.f9 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -5.0 -PREHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS nested_tbl_3_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE nested_tbl_3_n0 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS ORC -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@nested_tbl_3_n0 -POSTHOOK: query: CREATE TABLE nested_tbl_3_n0 (f1 boolean, f2 string) PARTITIONED BY (f3 int) STORED AS ORC -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nested_tbl_3_n0 -PREHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n0 PARTITION(f3) -SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 -FROM nested_tbl_1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -PREHOOK: Output: default@nested_tbl_3_n0 -POSTHOOK: query: INSERT OVERWRITE TABLE nested_tbl_3_n0 PARTITION(f3) -SELECT s1.f1 AS f1, S1.f2 AS f2, s1.f6 AS f3 -FROM nested_tbl_1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -POSTHOOK: Output: default@nested_tbl_3_n0@f3=4 -POSTHOOK: Lineage: nested_tbl_3_n0 PARTITION(f3=4).f1 EXPRESSION [(nested_tbl_1_n0)nested_tbl_1_n0.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] -POSTHOOK: Lineage: nested_tbl_3_n0 PARTITION(f3=4).f2 EXPRESSION [(nested_tbl_1_n0)nested_tbl_1_n0.FieldSchema(name:s1, type:struct,f6:int>, comment:null), ] -PREHOOK: query: SELECT * FROM nested_tbl_3_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_3_n0 -PREHOOK: Input: default@nested_tbl_3_n0@f3=4 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM nested_tbl_3_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_3_n0 -POSTHOOK: Input: default@nested_tbl_3_n0@f3=4 -#### A masked pattern was here #### -false foo 4 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n0 -GROUP BY s3.f12[0].f14 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n0 -GROUP BY s3.f12[0].f14 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s3.f12, s1.f6 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s3.f12[0].f14 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 2796 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n0 -GROUP BY s3.f12[0].f14 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s3.f12[0].f14 -FROM nested_tbl_1_n0 -GROUP BY s3.f12[0].f14 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -1 14 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n0 -GROUP BY s4['key1'].f15 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n0 -GROUP BY s4['key1'].f15 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s4['key1'].f15 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1096 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n0 -GROUP BY s4['key1'].f15 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s4['key1'].f15 -FROM nested_tbl_1_n0 -GROUP BY s4['key1'].f15 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -1 1 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16[0].f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16[0].f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s5.f16, s1.f6 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s5.f16[0].f18.f19 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16[0].f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s5.f16[0].f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16[0].f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -1 14 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16.f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16.f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f6, s5.f16 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s5 (type: struct>>>) - outputColumnNames: s1, s5 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(s1.f6) - keys: s5.f16.f18.f19 (type: array) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: array) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: array) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 3196 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16.f18.f19 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s5.f16.f18.f19 -FROM nested_tbl_1_n0 -GROUP BY s5.f16.f18.f19 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -1 [14,28] -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20[0].f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20[0].f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s6['key1'].f20[0].f21.f22 (type: int), s1.f6 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20[0].f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20[0].f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20[0].f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -1 1 -PREHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20.f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20.f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nested_tbl_1_n0 - Pruned Column Paths: s1.f6 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: s1 (type: struct,f6:int>), s6 (type: map>>>>) - outputColumnNames: s1, s6 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(s1.f6) - keys: s6['key1'].f20.f21.f22 (type: array) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: array) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: array) - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: array) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20.f21.f22 -PREHOOK: type: QUERY -PREHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(s1.f6), s6['key1'].f20.f21.f22 -FROM nested_tbl_1_n0 -GROUP BY s6['key1'].f20.f21.f22 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nested_tbl_1_n0 -#### A masked pattern was here #### -1 [1] diff --git ql/src/test/results/clientpositive/order.q.out ql/src/test/results/clientpositive/order.q.out deleted file mode 100644 index ee25b7185e..0000000000 --- ql/src/test/results/clientpositive/order.q.out +++ /dev/null @@ -1,146 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT x.* FROM SRC x ORDER BY key limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT x.* FROM SRC x ORDER BY key limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT x.* FROM SRC x ORDER BY key limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT x.* FROM SRC x ORDER BY key limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -10 val_10 -100 val_100 -100 val_100 -103 val_103 -103 val_103 -104 val_104 -104 val_104 -PREHOOK: query: EXPLAIN -SELECT x.* FROM SRC x ORDER BY key desc limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT x.* FROM SRC x ORDER BY key desc limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: - - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT x.* FROM SRC x ORDER BY key desc limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT x.* FROM SRC x ORDER BY key desc limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -98 val_98 -98 val_98 -97 val_97 -97 val_97 -96 val_96 -95 val_95 -95 val_95 -92 val_92 -90 val_90 -90 val_90 diff --git ql/src/test/results/clientpositive/order3.q.out ql/src/test/results/clientpositive/order3.q.out deleted file mode 100644 index 7b8583294b..0000000000 --- ql/src/test/results/clientpositive/order3.q.out +++ /dev/null @@ -1,627 +0,0 @@ -PREHOOK: query: drop table if exists test_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table if exists test_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table test_n0(key int, value1 int, value2 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_n0 -POSTHOOK: query: create table test_n0(key int, value1 int, value2 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_n0 -PREHOOK: query: insert into table test_n0 values (1, 1, 'val111'), (1, 2, 'val121'), (1, 3, 'val131'), (2, 1, 'val211'), (2, 2, 'val221'), (2, 2, 'val222'), (2, 3, 'val231'), (2, 4, 'val241'), -(3, 1, 'val311'), (3, 2, 'val321'), (3, 2, 'val322'), (3, 3, 'val331'), (3, 3, 'val332'), (3, 3, 'val333'), (4, 1, 'val411') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@test_n0 -POSTHOOK: query: insert into table test_n0 values (1, 1, 'val111'), (1, 2, 'val121'), (1, 3, 'val131'), (2, 1, 'val211'), (2, 2, 'val221'), (2, 2, 'val222'), (2, 3, 'val231'), (2, 4, 'val241'), -(3, 1, 'val311'), (3, 2, 'val321'), (3, 2, 'val322'), (3, 3, 'val331'), (3, 3, 'val332'), (3, 3, 'val333'), (4, 1, 'val411') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@test_n0 -POSTHOOK: Lineage: test_n0.key SCRIPT [] -POSTHOOK: Lineage: test_n0.value1 SCRIPT [] -POSTHOOK: Lineage: test_n0.value2 SCRIPT [] -PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: key - Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -1 -2 -3 -PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value1 (type: int) - outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(value1) - keys: key (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: int), _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -1 3 -2 4 -3 3 -PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value1 (type: int) - outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(value1) - keys: key (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint), _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), 'AAA' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - ListSink - -PREHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -1 3 AAA -2 5 AAA -3 6 AAA -PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: key - Statistics: Num rows: 15 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - ListSink - -PREHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT T1.KEY AS MYKEY FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -1 -2 -3 -PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value1 (type: int) - outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(value1) - keys: key (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - ListSink - -PREHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT T1.KEY AS MYKEY, MAX(T1.VALUE1) AS MYVALUE1 FROM TEST_n0 T1 GROUP BY T1.KEY ORDER BY T1.KEY LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -1 3 -2 4 -3 3 -PREHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value1 (type: int) - outputColumnNames: key, value1 - Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(value1) - keys: key (type: int), 'AAA' (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), 'AAA' (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), 'AAA' (type: string) - Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int), 'AAA' (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col2 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), 'AAA' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 297 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - ListSink - -PREHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@test_n0 -#### A masked pattern was here #### -POSTHOOK: query: SELECT T1.KEY AS MYKEY, COUNT(T1.VALUE1) AS MYVALUE1, 'AAA' AS C FROM TEST_n0 T1 GROUP BY T1.KEY, 'AAA' ORDER BY T1.KEY, 'AAA' LIMIT 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_n0 -#### A masked pattern was here #### -1 3 AAA -2 5 AAA -3 6 AAA diff --git ql/src/test/results/clientpositive/outer_join_ppr.q.out ql/src/test/results/clientpositive/outer_join_ppr.q.out deleted file mode 100644 index 8f6841de4c..0000000000 --- ql/src/test/results/clientpositive/outer_join_ppr.q.out +++ /dev/null @@ -1,646 +0,0 @@ -PREHOOK: query: EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`src` -WHERE `key` < 20 AND `key` > 15) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`srcpart` -WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -17 val_17 17 val_17 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19 -PREHOOK: query: EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED - FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`src` -WHERE `key` < 20 AND `key` > 15) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`srcpart` -WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: FROM - src a - FULL OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -17 val_17 17 val_17 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19 diff --git ql/src/test/results/clientpositive/outer_reference_windowed.q.out ql/src/test/results/clientpositive/outer_reference_windowed.q.out deleted file mode 100644 index b8efa2c097..0000000000 --- ql/src/test/results/clientpositive/outer_reference_windowed.q.out +++ /dev/null @@ -1,945 +0,0 @@ -PREHOOK: query: DROP TABLE IF EXISTS e011_01 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS e011_01 -POSTHOOK: type: DROPTABLE -PREHOOK: query: DROP TABLE IF EXISTS e011_02 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS e011_02 -POSTHOOK: type: DROPTABLE -PREHOOK: query: DROP TABLE IF EXISTS e011_03 -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS e011_03 -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE e011_01 ( - c1 decimal(15,2), - c2 decimal(15,2)) - STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e011_01 -POSTHOOK: query: CREATE TABLE e011_01 ( - c1 decimal(15,2), - c2 decimal(15,2)) - STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e011_01 -PREHOOK: query: CREATE TABLE e011_02 ( - c1 decimal(15,2), - c2 decimal(15,2)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e011_02 -POSTHOOK: query: CREATE TABLE e011_02 ( - c1 decimal(15,2), - c2 decimal(15,2)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e011_02 -PREHOOK: query: CREATE TABLE e011_03 ( - c1 decimal(15,2), - c2 decimal(15,2)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@e011_03 -POSTHOOK: query: CREATE TABLE e011_03 ( - c1 decimal(15,2), - c2 decimal(15,2)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@e011_03 -PREHOOK: query: LOAD DATA - LOCAL INPATH '../../data/files/e011_01.txt' - OVERWRITE - INTO TABLE e011_01 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@e011_01 -POSTHOOK: query: LOAD DATA - LOCAL INPATH '../../data/files/e011_01.txt' - OVERWRITE - INTO TABLE e011_01 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@e011_01 -PREHOOK: query: INSERT INTO TABLE e011_02 - SELECT c1, c2 - FROM e011_01 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Output: default@e011_02 -POSTHOOK: query: INSERT INTO TABLE e011_02 - SELECT c1, c2 - FROM e011_01 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Output: default@e011_02 -POSTHOOK: Lineage: e011_02.c1 SIMPLE [(e011_01)e011_01.FieldSchema(name:c1, type:decimal(15,2), comment:null), ] -POSTHOOK: Lineage: e011_02.c2 SIMPLE [(e011_01)e011_01.FieldSchema(name:c2, type:decimal(15,2), comment:null), ] -PREHOOK: query: INSERT INTO TABLE e011_03 - SELECT c1, c2 - FROM e011_01 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Output: default@e011_03 -POSTHOOK: query: INSERT INTO TABLE e011_03 - SELECT c1, c2 - FROM e011_01 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Output: default@e011_03 -POSTHOOK: Lineage: e011_03.c1 SIMPLE [(e011_01)e011_01.FieldSchema(name:c1, type:decimal(15,2), comment:null), ] -POSTHOOK: Lineage: e011_03.c2 SIMPLE [(e011_01)e011_01.FieldSchema(name:c2, type:decimal(15,2), comment:null), ] -PREHOOK: query: ANALYZE TABLE e011_01 COMPUTE STATISTICS FOR COLUMNS -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@e011_01 -PREHOOK: Output: default@e011_01 -#### A masked pattern was here #### -POSTHOOK: query: ANALYZE TABLE e011_01 COMPUTE STATISTICS FOR COLUMNS -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@e011_01 -POSTHOOK: Output: default@e011_01 -#### A masked pattern was here #### -PREHOOK: query: ANALYZE TABLE e011_02 COMPUTE STATISTICS FOR COLUMNS -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@e011_02 -PREHOOK: Output: default@e011_02 -#### A masked pattern was here #### -POSTHOOK: query: ANALYZE TABLE e011_02 COMPUTE STATISTICS FOR COLUMNS -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@e011_02 -POSTHOOK: Output: default@e011_02 -#### A masked pattern was here #### -PREHOOK: query: ANALYZE TABLE e011_03 COMPUTE STATISTICS FOR COLUMNS -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@e011_03 -PREHOOK: Output: default@e011_03 -#### A masked pattern was here #### -POSTHOOK: query: ANALYZE TABLE e011_03 COMPUTE STATISTICS FOR COLUMNS -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@e011_03 -POSTHOOK: Output: default@e011_03 -#### A masked pattern was here #### -PREHOOK: query: describe formatted e011_01 -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@e011_01 -POSTHOOK: query: describe formatted e011_01 -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@e011_01 -# col_name data_type comment -c1 decimal(15,2) -c2 decimal(15,2) - -# Detailed Table Information -Database: default -#### A masked pattern was here #### -Retention: 0 -#### A masked pattern was here #### -Table Type: MANAGED_TABLE -Table Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"c1\":\"true\",\"c2\":\"true\"}} - bucketing_version 2 - numFiles 1 - numRows 4 - rawDataSize 12 - totalSize 16 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: explain select sum(sum(c1)) over() from e011_01 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(sum(c1)) over() from e011_01 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: e011_01 - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)) - outputColumnNames: c1 - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(c1) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: 0 (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: decimal(25,2)) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: decimal(25,2) - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: 0 ASC NULLS FIRST - partition by: 0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumHiveDecimal - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: decimal(35,2)) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(sum(c1)) over() from e011_01 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -#### A masked pattern was here #### -POSTHOOK: query: select sum(sum(c1)) over() from e011_01 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -#### A masked pattern was here #### -16.00 -PREHOOK: query: explain select sum(sum(c1)) over( - partition by c2 order by c1) - from e011_01 - group by e011_01.c1, e011_01.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(sum(c1)) over( - partition by c2 order by c1) - from e011_01 - group by e011_01.c1, e011_01.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: e011_01 - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) - outputColumnNames: c1, c2 - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(c1) - keys: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) - null sort order: az - sort order: ++ - Map-reduce partition columns: _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: decimal(25,2) - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS LAST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col2 - name: sum - window function: GenericUDAFSumHiveDecimal - window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: decimal(35,2)) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(sum(c1)) over( - partition by c2 order by c1) - from e011_01 - group by e011_01.c1, e011_01.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -#### A masked pattern was here #### -POSTHOOK: query: select sum(sum(c1)) over( - partition by c2 order by c1) - from e011_01 - group by e011_01.c1, e011_01.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -#### A masked pattern was here #### -1.00 -3.00 -5.00 -7.00 -PREHOOK: query: explain select sum(sum(e011_01.c1)) over( - partition by e011_01.c2 order by e011_01.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_01.c1, e011_01.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Input: default@e011_03 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(sum(e011_01.c1)) over( - partition by e011_01.c2 order by e011_01.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_01.c1, e011_01.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Input: default@e011_03 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: e011_01 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: decimal(15,2)) - TableScan - alias: e011_03 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: decimal(15,2)) - 1 _col0 (type: decimal(15,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col0) - keys: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) - null sort order: az - sort order: ++ - Map-reduce partition columns: _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: decimal(25,2) - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS LAST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col2 - name: sum - window function: GenericUDAFSumHiveDecimal - window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: decimal(35,2)) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(sum(e011_01.c1)) over( - partition by e011_01.c2 order by e011_01.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_01.c1, e011_01.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Input: default@e011_03 -#### A masked pattern was here #### -POSTHOOK: query: select sum(sum(e011_01.c1)) over( - partition by e011_01.c2 order by e011_01.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_01.c1, e011_01.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Input: default@e011_03 -#### A masked pattern was here #### -1.00 -3.00 -5.00 -7.00 -PREHOOK: query: explain select sum(sum(e011_01.c1)) over( - partition by e011_03.c2 order by e011_03.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c1, e011_03.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Input: default@e011_03 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(sum(e011_01.c1)) over( - partition by e011_03.c2 order by e011_03.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c1, e011_03.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Input: default@e011_03 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: e011_01 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: e011_03 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: decimal(15,2)) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: decimal(15,2)) - 1 _col0 (type: decimal(15,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col0) - keys: _col1 (type: decimal(15,2)), _col2 (type: decimal(15,2)) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: decimal(15,2)), _col0 (type: decimal(15,2)) - null sort order: az - sort order: ++ - Map-reduce partition columns: _col1 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: decimal(25,2)) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: decimal(15,2)), KEY.reducesinkkey0 (type: decimal(15,2)), VALUE._col0 (type: decimal(25,2)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: decimal(25,2) - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS LAST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col2 - name: sum - window function: GenericUDAFSumHiveDecimal - window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 672 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: decimal(35,2)) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(sum(e011_01.c1)) over( - partition by e011_03.c2 order by e011_03.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c1, e011_03.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Input: default@e011_03 -#### A masked pattern was here #### -POSTHOOK: query: select sum(sum(e011_01.c1)) over( - partition by e011_03.c2 order by e011_03.c1) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c1, e011_03.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Input: default@e011_03 -#### A masked pattern was here #### -1.00 -3.00 -5.00 -7.00 -PREHOOK: query: explain select sum(corr(e011_01.c1, e011_03.c1)) - over(partition by e011_01.c2 order by e011_03.c2) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c2, e011_01.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Input: default@e011_03 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(corr(e011_01.c1, e011_03.c1)) - over(partition by e011_01.c2 order by e011_03.c2) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c2, e011_01.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Input: default@e011_03 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: e011_01 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: decimal(15,2)) - TableScan - alias: e011_03 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: decimal(15,2)), c2 (type: decimal(15,2)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 4 Data size: 896 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: decimal(15,2)) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: decimal(15,2)) - 1 _col0 (type: decimal(15,2)) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 1792 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: corr(_col0, _col2) - keys: _col1 (type: decimal(15,2)), _col3 (type: decimal(15,2)) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: decimal(15,2)), _col1 (type: decimal(15,2)) - null sort order: az - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(15,2)) - Statistics: Num rows: 2 Data size: 704 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: corr(VALUE._col0) - keys: KEY._col0 (type: decimal(15,2)), KEY._col1 (type: decimal(15,2)) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: decimal(15,2), _col1: decimal(15,2), _col2: double - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS LAST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col2 - name: sum - window function: GenericUDAFSumDouble - window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(corr(e011_01.c1, e011_03.c1)) - over(partition by e011_01.c2 order by e011_03.c2) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c2, e011_01.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@e011_01 -PREHOOK: Input: default@e011_03 -#### A masked pattern was here #### -POSTHOOK: query: select sum(corr(e011_01.c1, e011_03.c1)) - over(partition by e011_01.c2 order by e011_03.c2) - from e011_01 - join e011_03 on e011_01.c1 = e011_03.c1 - group by e011_03.c2, e011_01.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@e011_01 -POSTHOOK: Input: default@e011_03 -#### A masked pattern was here #### -NULL -NULL -NULL -NULL diff --git ql/src/test/results/clientpositive/parallel_join0.q.out ql/src/test/results/clientpositive/parallel_join0.q.out deleted file mode 100644 index 9f2e1814bb..0000000000 --- ql/src/test/results/clientpositive/parallel_join0.q.out +++ /dev/null @@ -1,247 +0,0 @@ -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: src - filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - sort order: ++++ - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN FORMATTED -SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -{"CBOPlan":"{\n \"rels\": [\n {\n \"id\": \"0\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveTableScan\",\n \"table\": [\n \"default\",\n \"src\"\n ],\n \"table:alias\": \"src\",\n \"inputs\": [],\n \"rowCount\": 500.0,\n \"avgRowSize\": 9.624,\n \"rowType\": [\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"key\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"value\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"BLOCK__OFFSET__INSIDE__FILE\"\n },\n {\n \"type\": \"VARCHAR\",\n \"nullable\": true,\n \"precision\": 2147483647,\n \"name\": \"INPUT__FILE__NAME\"\n },\n {\n \"fields\": [\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"writeid\"\n },\n {\n \"type\": \"INTEGER\",\n \"nullable\": true,\n \"name\": \"bucketid\"\n },\n {\n \"type\": \"BIGINT\",\n \"nullable\": true,\n \"name\": \"rowid\"\n }\n ],\n \"name\": \"ROW__ID\"\n }\n ],\n \"colStats\": [\n {\n \"name\": \"key\",\n \"ndv\": 316\n },\n {\n \"name\": \"value\",\n \"ndv\": 307\n }\n ]\n },\n {\n \"id\": \"1\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter\",\n \"condition\": {\n \"op\": {\n \"name\": \"<\",\n \"kind\": \"LESS_THAN\",\n \"syntax\": \"BINARY\"\n },\n \"operands\": [\n {\n \"op\": {\n \"name\": \"CAST\",\n \"kind\": \"CAST\",\n \"syntax\": \"SPECIAL\"\n },\n \"operands\": [\n {\n \"input\": 0,\n \"name\": \"$0\"\n }\n ],\n \"type\": {\n \"type\": \"DOUBLE\",\n \"nullable\": true\n }\n },\n {\n \"literal\": 10,\n \"type\": {\n \"type\": \"DOUBLE\",\n \"nullable\": false\n }\n }\n ]\n },\n \"rowCount\": 166.66666666666666\n },\n {\n \"id\": \"2\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"key\",\n \"value\"\n ],\n \"exprs\": [\n {\n \"input\": 0,\n \"name\": \"$0\"\n },\n {\n \"input\": 1,\n \"name\": \"$1\"\n }\n ],\n \"rowCount\": 166.66666666666666\n },\n {\n \"id\": \"3\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveJoin\",\n \"condition\": {\n \"literal\": true,\n \"type\": {\n \"type\": \"BOOLEAN\",\n \"nullable\": false\n }\n },\n \"joinType\": \"inner\",\n \"algorithm\": \"none\",\n \"cost\": \"not available\",\n \"inputs\": [\n \"2\",\n \"2\"\n ],\n \"rowCount\": 27777.777777777774\n },\n {\n \"id\": \"4\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject\",\n \"fields\": [\n \"key\",\n \"value\",\n \"key0\",\n \"value0\"\n ],\n \"exprs\": [\n {\n \"input\": 0,\n \"name\": \"$0\"\n },\n {\n \"input\": 1,\n \"name\": \"$1\"\n },\n {\n \"input\": 2,\n \"name\": \"$2\"\n },\n {\n \"input\": 3,\n \"name\": \"$3\"\n }\n ],\n \"rowCount\": 27777.777777777774\n },\n {\n \"id\": \"5\",\n \"relOp\": \"org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveSortExchange\",\n \"distribution\": {\n \"type\": \"ANY\"\n },\n \"collation\": [\n {\n \"field\": 0,\n \"direction\": \"ASCENDING\",\n \"nulls\": \"LAST\"\n },\n {\n \"field\": 1,\n \"direction\": \"ASCENDING\",\n \"nulls\": \"LAST\"\n },\n {\n \"field\": 2,\n \"direction\": \"ASCENDING\",\n \"nulls\": \"LAST\"\n },\n {\n \"field\": 3,\n \"direction\": \"ASCENDING\",\n \"nulls\": \"LAST\"\n }\n ],\n \"rowCount\": 27777.777777777774\n }\n ]\n}","cboInfo":"Plan optimized by CBO.","STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(UDFToDouble(key) < 10.0D) (type: boolean)","Statistics:":"Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE","table:":"src","isTempTable:":"false","OperatorId:":"TS_0","children":{"Filter Operator":{"predicate:":"(UDFToDouble(key) < 10.0D) (type: boolean)","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_13","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_2","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"null sort order:":"","sort order:":"","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_6"}}}}}}}},{"TableScan":{"alias:":"src","columns:":["key","value"],"database:":"default","filterExpr:":"(UDFToDouble(key) < 10.0D) (type: boolean)","Statistics:":"Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE","table:":"src","isTempTable:":"false","OperatorId:":"TS_3","children":{"Filter Operator":{"predicate:":"(UDFToDouble(key) < 10.0D) (type: boolean)","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"FIL_14","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","columnExprMap:":{"_col0":"key","_col1":"value"},"outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_5","children":{"Reduce Output Operator":{"columnExprMap:":{"VALUE._col0":"_col0","VALUE._col1":"_col1"},"null sort order:":"","sort order:":"","Statistics:":"Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: string), _col1 (type: string)","OperatorId:":"RS_7"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"columnExprMap:":{"_col0":"0:VALUE._col0","_col1":"0:VALUE._col1","_col2":"1:VALUE._col0","_col3":"1:VALUE._col1"},"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"JOIN_8","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"},"OperatorId:":"FS_15"}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"columns:":["_col0","_col1","_col2","_col3"],"OperatorId:":"TS_16","children":{"Reduce Output Operator":{"columnExprMap:":{"KEY.reducesinkkey0":"_col0","KEY.reducesinkkey1":"_col1","KEY.reducesinkkey2":"_col2","KEY.reducesinkkey3":"_col3"},"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","null sort order:":"zzzz","sort order:":"++++","Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"RS_10"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","columnExprMap:":{"_col0":"KEY.reducesinkkey0","_col1":"KEY.reducesinkkey1","_col2":"KEY.reducesinkkey2","_col3":"KEY.reducesinkkey3"},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","OperatorId:":"SEL_11","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 27556 Data size: 9809936 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"},"OperatorId:":"FS_12"}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_17"}}}}}} -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, - src2.key as k2, src2.value as v2 FROM - (SELECT * FROM src WHERE src.key < 10) src1 - JOIN - (SELECT * FROM src WHERE src.key < 10) src2 - SORT BY k1, v1, k2, v2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 0 val_0 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 2 val_2 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 4 val_4 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 5 val_5 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 8 val_8 -0 val_0 9 val_9 -0 val_0 9 val_9 -0 val_0 9 val_9 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 0 val_0 -2 val_2 2 val_2 -2 val_2 4 val_4 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 5 val_5 -2 val_2 8 val_8 -2 val_2 9 val_9 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 0 val_0 -4 val_4 2 val_2 -4 val_4 4 val_4 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 5 val_5 -4 val_4 8 val_8 -4 val_4 9 val_9 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 0 val_0 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 2 val_2 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 4 val_4 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 5 val_5 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 8 val_8 -5 val_5 9 val_9 -5 val_5 9 val_9 -5 val_5 9 val_9 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 0 val_0 -8 val_8 2 val_2 -8 val_8 4 val_4 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 5 val_5 -8 val_8 8 val_8 -8 val_8 9 val_9 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 0 val_0 -9 val_9 2 val_2 -9 val_9 4 val_4 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 5 val_5 -9 val_9 8 val_8 -9 val_9 9 val_9 diff --git ql/src/test/results/clientpositive/parquet_no_row_serde.q.out ql/src/test/results/clientpositive/parquet_no_row_serde.q.out deleted file mode 100644 index e723fa8298..0000000000 --- ql/src/test/results/clientpositive/parquet_no_row_serde.q.out +++ /dev/null @@ -1,204 +0,0 @@ -PREHOOK: query: drop table tbl_rc -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table tbl_rc -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table tbl_parquet -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table tbl_parquet -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table tbl_rc (val decimal(10,0)) -row format serde 'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe' stored as rcfile -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl_rc -POSTHOOK: query: create table tbl_rc (val decimal(10,0)) -row format serde 'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe' stored as rcfile -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl_rc -PREHOOK: query: create table tbl_parquet (val decimal(10,0)) -STORED AS PARQUET -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl_parquet -POSTHOOK: query: create table tbl_parquet (val decimal(10,0)) -STORED AS PARQUET -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl_parquet -PREHOOK: query: insert into table tbl_rc values(101) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@tbl_rc -POSTHOOK: query: insert into table tbl_rc values(101) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@tbl_rc -POSTHOOK: Lineage: tbl_rc.val SCRIPT [] -PREHOOK: query: insert into table tbl_parquet values(101) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@tbl_parquet -POSTHOOK: query: insert into table tbl_parquet values(101) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@tbl_parquet -POSTHOOK: Lineage: tbl_parquet.val SCRIPT [] -PREHOOK: query: explain vectorization expression -select val, round(val, -1) from tbl_rc order by val -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_rc -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization expression -select val, round(val, -1) from tbl_rc order by val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_rc -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tbl_rc - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Select Operator - expressions: val (type: decimal(10,0)), round(val, -1) (type: decimal(11,0)) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 2] - selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 0:decimal(10,0), decimalPlaces -1) -> 2:decimal(11,0) - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(10,0)) - null sort order: z - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: decimal(11,0)) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.row.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.RCFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain vectorization expression -select val, round(val, -1) from tbl_parquet order by val -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_parquet -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization expression -select val, round(val, -1) from tbl_parquet order by val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_parquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tbl_parquet - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: val (type: decimal(10,0)), round(val, -1) (type: decimal(11,0)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(10,0)) - null sort order: z - sort order: + - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: decimal(11,0)) - Map Vectorization: - enabled: false - enabledConditionsNotMet: Row deserialization of vectorized input format not supported IS false, hive.vectorized.use.vectorized.input.format IS false - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: decimal(10,0)), VALUE._col0 (type: decimal(11,0)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: drop table tbl_rc -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@tbl_rc -PREHOOK: Output: default@tbl_rc -POSTHOOK: query: drop table tbl_rc -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@tbl_rc -POSTHOOK: Output: default@tbl_rc -PREHOOK: query: drop table tbl_parquet -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@tbl_parquet -PREHOOK: Output: default@tbl_parquet -POSTHOOK: query: drop table tbl_parquet -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@tbl_parquet -POSTHOOK: Output: default@tbl_parquet diff --git ql/src/test/results/clientpositive/parquet_vectorization_1.q.out ql/src/test/results/clientpositive/parquet_vectorization_1.q.out deleted file mode 100644 index b408d6e312..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_1.q.out +++ /dev/null @@ -1,186 +0,0 @@ -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT VAR_POP(ctinyint), - (VAR_POP(ctinyint) / -26.28), - SUM(cfloat), - (-1.389 + SUM(cfloat)), - (SUM(cfloat) * (-1.389 + SUM(cfloat))), - MAX(ctinyint), - (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), - MAX(cint), - (MAX(cint) * 79.553), - VAR_SAMP(cdouble), - (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), - COUNT(cint), - (-563 % MAX(cint)) -FROM alltypesparquet -WHERE (((cdouble > ctinyint) - AND (cboolean2 > 0)) - OR ((cbigint < ctinyint) - OR ((cint > cbigint) - OR (cboolean1 < 0)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT VAR_POP(ctinyint), - (VAR_POP(ctinyint) / -26.28), - SUM(cfloat), - (-1.389 + SUM(cfloat)), - (SUM(cfloat) * (-1.389 + SUM(cfloat))), - MAX(ctinyint), - (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), - MAX(cint), - (MAX(cint) * 79.553), - VAR_SAMP(cdouble), - (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), - COUNT(cint), - (-563 % MAX(cint)) -FROM alltypesparquet -WHERE (((cdouble > ctinyint) - AND (cboolean2 > 0)) - OR ((cbigint < ctinyint) - OR ((cint > cbigint) - OR (cboolean1 < 0)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cboolean1 < 0) or (cbigint < UDFToLong(ctinyint)) or (UDFToLong(cint) > cbigint) or ((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterLongColLessLongScalar(col 10:boolean, val 0), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0))) - predicate: ((cboolean1 < 0) or (cbigint < UDFToLong(ctinyint)) or (UDFToLong(cint) > cbigint) or ((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0))) (type: boolean) - Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 4, 2, 5, 14, 17, 18] - selectExpressions: CastLongToDouble(col 0:tinyint) -> 14:double, DoubleColMultiplyDoubleColumn(col 15:double, col 16:double)(children: CastLongToDouble(col 0:tinyint) -> 15:double, CastLongToDouble(col 0:tinyint) -> 16:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 18:double - Statistics: Num rows: 12288 Data size: 330276 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2) - Group By Vectorization: - aggregators: VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFSumDouble(col 14:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFMaxLong(col 0:tinyint) -> tinyint, VectorUDAFMaxLong(col 2:int) -> int, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint, VectorUDAFCount(col 2:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: tinyint), _col5 (type: int), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), max(VALUE._col4), max(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), count(VALUE._col9) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ((_col0 - ((_col1 * _col1) / _col2)) / _col2) (type: double), (((_col0 - ((_col1 * _col1) / _col2)) / _col2) / -26.28D) (type: double), _col3 (type: double), (-1.389D + _col3) (type: double), (_col3 * (-1.389D + _col3)) (type: double), _col4 (type: tinyint), (- (_col3 * (-1.389D + _col3))) (type: double), _col5 (type: int), (CAST( _col5 AS decimal(10,0)) * 79.553) (type: decimal(16,3)), ((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END) (type: double), (10.175D % (- (_col3 * (-1.389D + _col3)))) (type: double), _col9 (type: bigint), (-563 % _col5) (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT VAR_POP(ctinyint), - (VAR_POP(ctinyint) / -26.28), - SUM(cfloat), - (-1.389 + SUM(cfloat)), - (SUM(cfloat) * (-1.389 + SUM(cfloat))), - MAX(ctinyint), - (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), - MAX(cint), - (MAX(cint) * 79.553), - VAR_SAMP(cdouble), - (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), - COUNT(cint), - (-563 % MAX(cint)) -FROM alltypesparquet -WHERE (((cdouble > ctinyint) - AND (cboolean2 > 0)) - OR ((cbigint < ctinyint) - OR ((cint > cbigint) - OR (cboolean1 < 0)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT VAR_POP(ctinyint), - (VAR_POP(ctinyint) / -26.28), - SUM(cfloat), - (-1.389 + SUM(cfloat)), - (SUM(cfloat) * (-1.389 + SUM(cfloat))), - MAX(ctinyint), - (-((SUM(cfloat) * (-1.389 + SUM(cfloat))))), - MAX(cint), - (MAX(cint) * 79.553), - VAR_SAMP(cdouble), - (10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))), - COUNT(cint), - (-563 % MAX(cint)) -FROM alltypesparquet -WHERE (((cdouble > ctinyint) - AND (cboolean2 > 0)) - OR ((cbigint < ctinyint) - OR ((cint > cbigint) - OR (cboolean1 < 0)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -1074.8302575472321 -40.899172661614614 -21997.674998402596 -21999.063998402595 4.839282601059194E8 62 -4.839282601059194E8 1073680599 85414512692.247 7.569848642620917E10 10.175 3745 -563 diff --git ql/src/test/results/clientpositive/parquet_vectorization_13.q.out ql/src/test/results/clientpositive/parquet_vectorization_13.q.out deleted file mode 100644 index 390a6c0185..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_13.q.out +++ /dev/null @@ -1,650 +0,0 @@ -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28789) - AND ((ctimestamp2 != -28788) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28789) - AND ((ctimestamp2 != -28788) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 12288 Data size: 1779902 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28789.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28788.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimal64ColLessDecimal64Scalar(col 15:decimal(11,4)/DECIMAL_64, val 97632155639)(children: CastLongToDecimal64(col 0:tinyint) -> 15:decimal(11,4)/DECIMAL_64))) - predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28789.0D) and (UDFToDouble(ctimestamp2) <> -28788.0D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] - selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) - Group By Vectorization: - aggregators: VectorUDAFMaxLong(col 0:tinyint) -> tinyint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumDouble(col 16:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFSumDouble(col 20:double) -> double, VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFMaxDouble(col 4:float) -> float, VectorUDAFMinLong(col 0:tinyint) -> tinyint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 10:boolean, col 0:tinyint, col 8:timestamp, col 4:float, col 6:string - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 693 Data size: 122752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - null sort order: zzzzz - sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 693 Data size: 122752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 693 Data size: 122752 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 693 Data size: 219772 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) - null sort order: zzzzzzzzzzzzzzzzzzzzz - sort order: +++++++++++++++++++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 693 Data size: 219772 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 693 Data size: 219772 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 40 - Statistics: Num rows: 40 Data size: 12846 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 12846 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 40 - Processor Tree: - ListSink - -PREHOOK: query: SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28789) - AND ((ctimestamp2 != -28788) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28789) - AND ((ctimestamp2 != -28788) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -true -55 1969-12-31 16:00:12.297 -55.0 1cGVWH7n1QU 55 -55 0 -55.0 -0.0 55.0 -4375.415 0.0 55.0 0.0 -10.175 -55.0 0.47781818181818186 -55.0 0.0 -55 -true -55 1969-12-31 16:00:13.15 -55.0 1cGVWH7n1QU 55 -55 0 -55.0 -0.0 55.0 -4375.415 0.0 55.0 0.0 -10.175 -55.0 0.47781818181818186 -55.0 0.0 -55 -true -56 1969-12-31 16:00:11.242 -56.0 cvLH6Eat2yFsyy7p 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 -true -56 1969-12-31 16:00:13.534 -56.0 1cGVWH7n1QU 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 -true -56 1969-12-31 16:00:14.038 -56.0 1cGVWH7n1QU 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 -true -56 1969-12-31 16:00:14.689 -56.0 cvLH6Eat2yFsyy7p 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 -true -56 1969-12-31 16:00:16.37 -56.0 cvLH6Eat2yFsyy7p 56 -56 0 -56.0 -0.0 56.0 -4454.9683 0.0 56.0 0.0 -10.175 -56.0 0.4692857142857143 -56.0 0.0 -56 -true -57 1969-12-31 16:00:11.534 -57.0 cvLH6Eat2yFsyy7p 57 -57 0 -57.0 -0.0 57.0 -4534.521 0.0 57.0 0.0 -10.175 -57.0 0.4610526315789474 -57.0 0.0 -57 -true -57 1969-12-31 16:00:13.365 -57.0 1cGVWH7n1QU 57 -57 0 -57.0 -0.0 57.0 -4534.521 0.0 57.0 0.0 -10.175 -57.0 0.4610526315789474 -57.0 0.0 -57 -true -57 1969-12-31 16:00:14.225 -57.0 821UdmGbkEf4j 57 -57 0 -57.0 -0.0 57.0 -4534.521 0.0 57.0 0.0 -10.175 -57.0 0.4610526315789474 -57.0 0.0 -57 -true -58 1969-12-31 16:00:12.918 -58.0 cvLH6Eat2yFsyy7p 58 -58 0 -58.0 -0.0 58.0 -4614.074 0.0 58.0 0.0 -10.175 -58.0 0.4531034482758621 -58.0 0.0 -58 -true -58 1969-12-31 16:00:13.209 -58.0 cvLH6Eat2yFsyy7p 58 -58 0 -58.0 -0.0 58.0 -4614.074 0.0 58.0 0.0 -10.175 -58.0 0.4531034482758621 -58.0 0.0 -58 -true -58 1969-12-31 16:00:14.933 -58.0 cvLH6Eat2yFsyy7p 58 -58 0 -58.0 -0.0 58.0 -4614.074 0.0 58.0 0.0 -10.175 -58.0 0.4531034482758621 -58.0 0.0 -58 -true -59 1969-12-31 16:00:11.065 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:11.109 -59.0 1cGVWH7n1QU 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:11.231 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:11.758 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:12.227 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:15.242 -59.0 821UdmGbkEf4j 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:15.278 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:16.069 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -59 1969-12-31 16:00:16.125 -59.0 cvLH6Eat2yFsyy7p 59 -59 0 -59.0 -0.0 59.0 -4693.627 0.0 59.0 0.0 -10.175 -59.0 0.44542372881355935 -59.0 0.0 -59 -true -60 1969-12-31 16:00:11.849 -60.0 1cGVWH7n1QU 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 -true -60 1969-12-31 16:00:12.223 -60.0 1cGVWH7n1QU 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 -true -60 1969-12-31 16:00:12.291 -60.0 821UdmGbkEf4j 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 -true -60 1969-12-31 16:00:13.567 -60.0 821UdmGbkEf4j 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 -true -60 1969-12-31 16:00:15.188 -60.0 cvLH6Eat2yFsyy7p 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 -true -60 1969-12-31 16:00:16.165 -60.0 cvLH6Eat2yFsyy7p 60 -60 0 -60.0 -0.0 60.0 -4773.18 0.0 60.0 0.0 -10.175 -60.0 0.438 -60.0 0.0 -60 -true -61 1969-12-31 16:00:12.045 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:12.75 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:15.325 -61.0 821UdmGbkEf4j 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:15.694 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -62 1969-12-31 16:00:13.677 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:14.872 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:15.153 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -63 1969-12-31 16:00:13.752 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -63 1969-12-31 16:00:14.899 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -63 1969-12-31 16:00:15.827 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -64 1969-12-31 16:00:11.952 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:12.857 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28801.388) - AND ((ctimestamp2 != -28801.3359999999999999) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28801.388) - AND ((ctimestamp2 != -28801.3359999999999999) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 12288 Data size: 1779902 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val 3569.0), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 10.175), FilterLongColNotEqualLongScalar(col 10:boolean, val 1)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28801.388)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val -28801.336)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterDecimal64ColLessDecimal64Scalar(col 15:decimal(11,4)/DECIMAL_64, val 97632155639)(children: CastLongToDecimal64(col 0:tinyint) -> 15:decimal(11,4)/DECIMAL_64))) - predicate: (((cfloat < 3569.0) and (cdouble <= 10.175D) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -28801.388D) and (UDFToDouble(ctimestamp2) <> -28801.336D) and (CAST( ctinyint AS decimal(11,4)) < 9763215.5639))) (type: boolean) - Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [10, 0, 8, 4, 6, 4, 16, 17, 20] - selectExpressions: DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 16:double, CastLongToDouble(col 0:tinyint) -> 17:double, DoubleColMultiplyDoubleColumn(col 18:double, col 19:double)(children: CastLongToDouble(col 0:tinyint) -> 18:double, CastLongToDouble(col 0:tinyint) -> 19:double) -> 20:double - Statistics: Num rows: 1386 Data size: 200984 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(_col1), sum(_col3), sum(_col6), sum(_col5), count(_col3), sum(_col8), sum(_col7), count(_col1), max(_col3), min(_col1) - Group By Vectorization: - aggregators: VectorUDAFMaxLong(col 0:tinyint) -> tinyint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumDouble(col 16:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFSumDouble(col 20:double) -> double, VectorUDAFSumDouble(col 17:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFMaxDouble(col 4:float) -> float, VectorUDAFMinLong(col 0:tinyint) -> tinyint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 10:boolean, col 0:tinyint, col 8:timestamp, col 4:float, col 6:string - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 693 Data size: 122752 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - null sort order: zzzzz - sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 693 Data size: 122752 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: bigint), _col10 (type: double), _col11 (type: double), _col12 (type: bigint), _col13 (type: float), _col14 (type: tinyint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), count(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 693 Data size: 122752 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * _col3) (type: float), power(((_col7 - ((_col8 * _col8) / _col9)) / _col9), 0.5) (type: double), (- _col6) (type: double), power(((_col10 - ((_col11 * _col11) / _col12)) / _col12), 0.5) (type: double), (CAST( ((- _col1) + _col5) AS decimal(3,0)) - 10.175) (type: decimal(7,3)), (- (- _col6)) (type: double), (-26.28D / (- (- _col6))) (type: double), _col13 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col14 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 693 Data size: 219772 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), _col5 (type: tinyint), _col6 (type: tinyint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: decimal(7,3)), _col16 (type: double), _col17 (type: double), _col18 (type: float), _col19 (type: double), _col20 (type: tinyint) - null sort order: zzzzzzzzzzzzzzzzzzzzz - sort order: +++++++++++++++++++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 693 Data size: 219772 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey2 (type: timestamp), KEY.reducesinkkey3 (type: float), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: tinyint), KEY.reducesinkkey6 (type: tinyint), KEY.reducesinkkey7 (type: tinyint), KEY.reducesinkkey8 (type: double), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: double), KEY.reducesinkkey10 (type: double), KEY.reducesinkkey14 (type: double), KEY.reducesinkkey15 (type: decimal(7,3)), KEY.reducesinkkey16 (type: double), KEY.reducesinkkey17 (type: double), KEY.reducesinkkey18 (type: float), KEY.reducesinkkey19 (type: double), KEY.reducesinkkey20 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 693 Data size: 219772 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 40 - Statistics: Num rows: 40 Data size: 12846 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 12846 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 40 - Processor Tree: - ListSink - -PREHOOK: query: SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28801.388) - AND ((ctimestamp2 != -28801.3359999999999999) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT cboolean1, - ctinyint, - ctimestamp1, - cfloat, - cstring1, - (-(ctinyint)) as c1, - MAX(ctinyint) as c2, - ((-(ctinyint)) + MAX(ctinyint)) as c3, - SUM(cfloat) as c4, - (SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) as c5, - (-(SUM(cfloat))) as c6, - (79.553 * cfloat) as c7, - STDDEV_POP(cfloat) as c8, - (-(SUM(cfloat))) as c9, - STDDEV_POP(ctinyint) as c10, - (((-(ctinyint)) + MAX(ctinyint)) - 10.175) as c11, - (-((-(SUM(cfloat))))) as c12, - (-26.28 / (-((-(SUM(cfloat)))))) as c13, - MAX(cfloat) as c14, - ((SUM(cfloat) * ((-(ctinyint)) + MAX(ctinyint))) / ctinyint) as c15, - MIN(ctinyint) as c16 -FROM alltypesparquet -WHERE (((cfloat < 3569) - AND ((10.175 >= cdouble) - AND (cboolean1 != 1))) - OR ((ctimestamp1 > -28801.388) - AND ((ctimestamp2 != -28801.3359999999999999) - AND (ctinyint < 9763215.5639)))) -GROUP BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1 -ORDER BY cboolean1, ctinyint, ctimestamp1, cfloat, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11, c12, c13, c14, c15, c16 -LIMIT 40 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -true -61 1969-12-31 16:00:00.554 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:02.339 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:02.497 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:03.742 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:07.538 -61.0 821UdmGbkEf4j 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:09.809 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:10.713 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:12.045 -61.0 1cGVWH7n1QU 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -61 1969-12-31 16:00:12.75 -61.0 cvLH6Eat2yFsyy7p 61 -61 0 -61.0 -0.0 61.0 -4852.733 0.0 61.0 0.0 -10.175 -61.0 0.4308196721311476 -61.0 0.0 -61 -true -62 1969-12-31 16:00:00.337 -62.0 1cGVWH7n1QU 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:00.659 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:00.684 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:01.419 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:02.123 -62.0 1cGVWH7n1QU 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:02.922 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:04.978 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:07.756 -62.0 1cGVWH7n1QU 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:07.847 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:07.903 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:13.677 -62.0 cvLH6Eat2yFsyy7p 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:14.872 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -62 1969-12-31 16:00:15.153 -62.0 821UdmGbkEf4j 62 -62 0 -62.0 -0.0 62.0 -4932.286 0.0 62.0 0.0 -10.175 -62.0 0.4238709677419355 -62.0 0.0 -62 -true -63 1969-12-31 16:00:05.654 -63.0 821UdmGbkEf4j 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -63 1969-12-31 16:00:07.623 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -63 1969-12-31 16:00:09.14 -63.0 821UdmGbkEf4j 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -63 1969-12-31 16:00:13.752 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -63 1969-12-31 16:00:14.899 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -63 1969-12-31 16:00:15.827 -63.0 cvLH6Eat2yFsyy7p 63 -63 0 -63.0 -0.0 63.0 -5011.839 0.0 63.0 0.0 -10.175 -63.0 0.41714285714285715 -63.0 0.0 -63 -true -64 1969-12-31 15:59:58.959 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:00.013 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:00.172 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:00.631 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:01.305 -64.0 cvLH6Eat2yFsyy7p 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:01.79 -64.0 1cGVWH7n1QU 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:02.496 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:03.088 -64.0 cvLH6Eat2yFsyy7p 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:04.662 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:10.273 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:11.952 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 -true -64 1969-12-31 16:00:12.857 -64.0 821UdmGbkEf4j 64 -64 0 -64.0 -0.0 64.0 -5091.392 0.0 64.0 0.0 -10.175 -64.0 0.410625 -64.0 0.0 -64 diff --git ql/src/test/results/clientpositive/parquet_vectorization_2.q.out ql/src/test/results/clientpositive/parquet_vectorization_2.q.out deleted file mode 100644 index eb2861a244..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_2.q.out +++ /dev/null @@ -1,194 +0,0 @@ -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT AVG(csmallint), - (AVG(csmallint) % -563), - (AVG(csmallint) + 762), - SUM(cfloat), - VAR_POP(cbigint), - (-(VAR_POP(cbigint))), - (SUM(cfloat) - AVG(csmallint)), - COUNT(*), - (-((SUM(cfloat) - AVG(csmallint)))), - (VAR_POP(cbigint) - 762), - MIN(ctinyint), - ((-(VAR_POP(cbigint))) + MIN(ctinyint)), - AVG(cdouble), - (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) -FROM alltypesparquet -WHERE (((ctimestamp1 < ctimestamp2) - AND ((cstring2 LIKE 'b%') - AND (cfloat <= -5638.15))) - OR ((cdouble < ctinyint) - AND ((-10669 != ctimestamp2) - OR (359 > cint)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT AVG(csmallint), - (AVG(csmallint) % -563), - (AVG(csmallint) + 762), - SUM(cfloat), - VAR_POP(cbigint), - (-(VAR_POP(cbigint))), - (SUM(cfloat) - AVG(csmallint)), - COUNT(*), - (-((SUM(cfloat) - AVG(csmallint)))), - (VAR_POP(cbigint) - 762), - MIN(ctinyint), - ((-(VAR_POP(cbigint))) + MIN(ctinyint)), - AVG(cdouble), - (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) -FROM alltypesparquet -WHERE (((ctimestamp1 < ctimestamp2) - AND ((cstring2 LIKE 'b%') - AND (cfloat <= -5638.15))) - OR ((cdouble < ctinyint) - AND ((-10669 != ctimestamp2) - OR (359 > cint)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean) - Statistics: Num rows: 12288 Data size: 1908244 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterExprOrExpr(children: FilterDoubleColNotEqualDoubleScalar(col 14:double, val -10669.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), FilterLongColLessLongScalar(col 2:int, val 359))), FilterExprAndExpr(children: FilterTimestampColLessTimestampColumn(col 8:timestamp, col 9:timestamp), FilterStringColLikeStringScalar(col 7:string, pattern b%), FilterDoubleColLessEqualDoubleScalar(col 4:float, val -5638.14990234375))) - predicate: (((cdouble < UDFToDouble(ctinyint)) and ((UDFToDouble(ctimestamp2) <> -10669.0D) or (cint < 359))) or ((ctimestamp1 < ctimestamp2) and (cstring2 like 'b%') and (cfloat <= -5638.15))) (type: boolean) - Statistics: Num rows: 4096 Data size: 636272 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: csmallint (type: smallint), cfloat (type: float), cbigint (type: bigint), ctinyint (type: tinyint), cdouble (type: double), UDFToDouble(cbigint) (type: double), (UDFToDouble(cbigint) * UDFToDouble(cbigint)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [1, 4, 3, 0, 5, 15, 18] - selectExpressions: CastLongToDouble(col 3:bigint) -> 15:double, DoubleColMultiplyDoubleColumn(col 16:double, col 17:double)(children: CastLongToDouble(col 3:bigint) -> 16:double, CastLongToDouble(col 3:bigint) -> 17:double) -> 18:double - Statistics: Num rows: 4096 Data size: 636272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col0), count(_col0), sum(_col1), sum(_col6), sum(_col5), count(_col2), count(), min(_col3), sum(_col4), count(_col4) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 1:smallint) -> bigint, VectorUDAFCount(col 1:smallint) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFSumDouble(col 15:double) -> double, VectorUDAFCount(col 3:bigint) -> bigint, VectorUDAFCountStar(*) -> bigint, VectorUDAFMinLong(col 0:tinyint) -> tinyint, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: tinyint), _col8 (type: double), _col9 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), count(VALUE._col6), min(VALUE._col7), sum(VALUE._col8), count(VALUE._col9) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 76 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToDouble(_col0) / _col1) (type: double), ((UDFToDouble(_col0) / _col1) % -563.0D) (type: double), ((UDFToDouble(_col0) / _col1) + 762.0D) (type: double), _col2 (type: double), ((_col3 - ((_col4 * _col4) / _col5)) / _col5) (type: double), (- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) (type: double), (_col2 - (UDFToDouble(_col0) / _col1)) (type: double), _col6 (type: bigint), (- (_col2 - (UDFToDouble(_col0) / _col1))) (type: double), (((_col3 - ((_col4 * _col4) / _col5)) / _col5) - 762.0D) (type: double), _col7 (type: tinyint), ((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) (type: double), (_col8 / _col9) (type: double), (((- ((_col3 - ((_col4 * _col4) / _col5)) / _col5)) + UDFToDouble(_col7)) - _col2) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT AVG(csmallint), - (AVG(csmallint) % -563), - (AVG(csmallint) + 762), - SUM(cfloat), - VAR_POP(cbigint), - (-(VAR_POP(cbigint))), - (SUM(cfloat) - AVG(csmallint)), - COUNT(*), - (-((SUM(cfloat) - AVG(csmallint)))), - (VAR_POP(cbigint) - 762), - MIN(ctinyint), - ((-(VAR_POP(cbigint))) + MIN(ctinyint)), - AVG(cdouble), - (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) -FROM alltypesparquet -WHERE (((ctimestamp1 < ctimestamp2) - AND ((cstring2 LIKE 'b%') - AND (cfloat <= -5638.15))) - OR ((cdouble < ctinyint) - AND ((-10669 != ctimestamp2) - OR (359 > cint)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT AVG(csmallint), - (AVG(csmallint) % -563), - (AVG(csmallint) + 762), - SUM(cfloat), - VAR_POP(cbigint), - (-(VAR_POP(cbigint))), - (SUM(cfloat) - AVG(csmallint)), - COUNT(*), - (-((SUM(cfloat) - AVG(csmallint)))), - (VAR_POP(cbigint) - 762), - MIN(ctinyint), - ((-(VAR_POP(cbigint))) + MIN(ctinyint)), - AVG(cdouble), - (((-(VAR_POP(cbigint))) + MIN(ctinyint)) - SUM(cfloat)) -FROM alltypesparquet -WHERE (((ctimestamp1 < ctimestamp2) - AND ((cstring2 LIKE 'b%') - AND (cfloat <= -5638.15))) - OR ((cdouble < ctinyint) - AND ((-10669 != ctimestamp2) - OR (359 > cint)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --5646.467075892857 -16.467075892856883 -4884.467075892857 -2839.634998679161 1.49936299222378906E18 -1.49936299222378906E18 2806.832077213696 3584 -2806.832077213696 1.49936299222378829E18 -64 -1.49936299222378906E18 -5650.1297631138395 -1.49936299222378624E18 diff --git ql/src/test/results/clientpositive/parquet_vectorization_3.q.out ql/src/test/results/clientpositive/parquet_vectorization_3.q.out deleted file mode 100644 index 3acf947d52..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_3.q.out +++ /dev/null @@ -1,204 +0,0 @@ -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT STDDEV_SAMP(csmallint), - (STDDEV_SAMP(csmallint) - 10.175), - STDDEV_POP(ctinyint), - (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), - (-(STDDEV_POP(ctinyint))), - (STDDEV_SAMP(csmallint) % 79.553), - (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), - STDDEV_SAMP(cfloat), - (-(STDDEV_SAMP(csmallint))), - SUM(cfloat), - ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), - (-((STDDEV_SAMP(csmallint) - 10.175))), - AVG(cint), - (-3728 - STDDEV_SAMP(csmallint)), - STDDEV_POP(cint), - (AVG(cint) / STDDEV_SAMP(cfloat)) -FROM alltypesparquet -WHERE (((cint <= cfloat) - AND ((79.553 != cbigint) - AND (ctimestamp2 = -29071))) - OR ((cbigint > cdouble) - AND ((79.553 <= csmallint) - AND (ctimestamp1 > ctimestamp2)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT STDDEV_SAMP(csmallint), - (STDDEV_SAMP(csmallint) - 10.175), - STDDEV_POP(ctinyint), - (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), - (-(STDDEV_POP(ctinyint))), - (STDDEV_SAMP(csmallint) % 79.553), - (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), - STDDEV_SAMP(cfloat), - (-(STDDEV_SAMP(csmallint))), - SUM(cfloat), - ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), - (-((STDDEV_SAMP(csmallint) - 10.175))), - AVG(cint), - (-3728 - STDDEV_SAMP(csmallint)), - STDDEV_POP(cint), - (AVG(cint) / STDDEV_SAMP(cfloat)) -FROM alltypesparquet -WHERE (((cint <= cfloat) - AND ((79.553 != cbigint) - AND (ctimestamp2 = -29071))) - OR ((cbigint > cdouble) - AND ((79.553 <= csmallint) - AND (ctimestamp1 > ctimestamp2)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D)) or ((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2))) (type: boolean) - Statistics: Num rows: 12288 Data size: 1027540 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 13:float), FilterDecimalColNotEqualDecimalScalar(col 14:decimal(22,3), val 79.553)(children: CastLongToDecimal(col 3:bigint) -> 14:decimal(22,3)), FilterDoubleColEqualDoubleScalar(col 15:double, val -29071.0)(children: CastTimestampToDouble(col 9:timestamp) -> 15:double)), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 16:double, col 5:double)(children: CastLongToDouble(col 3:bigint) -> 16:double), FilterDecimal64ColGreaterEqualDecimal64Scalar(col 17:decimal(8,3)/DECIMAL_64, val 79553)(children: CastLongToDecimal64(col 1:smallint) -> 17:decimal(8,3)/DECIMAL_64), FilterTimestampColGreaterTimestampColumn(col 8:timestamp, col 9:timestamp))) - predicate: (((UDFToFloat(cint) <= cfloat) and (CAST( cbigint AS decimal(22,3)) <> 79.553) and (UDFToDouble(ctimestamp2) = -29071.0D)) or ((UDFToDouble(cbigint) > cdouble) and (CAST( csmallint AS decimal(8,3)) >= 79.553) and (ctimestamp1 > ctimestamp2))) (type: boolean) - Statistics: Num rows: 2503 Data size: 209380 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cint (type: int), UDFToDouble(csmallint) (type: double), (UDFToDouble(csmallint) * UDFToDouble(csmallint)) (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), UDFToDouble(cfloat) (type: double), (UDFToDouble(cfloat) * UDFToDouble(cfloat)) (type: double), UDFToDouble(cint) (type: double), (UDFToDouble(cint) * UDFToDouble(cint)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [1, 0, 4, 2, 18, 21, 22, 25, 4, 26, 27, 30] - selectExpressions: CastLongToDouble(col 1:smallint) -> 18:double, DoubleColMultiplyDoubleColumn(col 19:double, col 20:double)(children: CastLongToDouble(col 1:smallint) -> 19:double, CastLongToDouble(col 1:smallint) -> 20:double) -> 21:double, CastLongToDouble(col 0:tinyint) -> 22:double, DoubleColMultiplyDoubleColumn(col 23:double, col 24:double)(children: CastLongToDouble(col 0:tinyint) -> 23:double, CastLongToDouble(col 0:tinyint) -> 24:double) -> 25:double, DoubleColMultiplyDoubleColumn(col 4:double, col 4:double)(children: col 4:float, col 4:float) -> 26:double, CastLongToDouble(col 2:int) -> 27:double, DoubleColMultiplyDoubleColumn(col 28:double, col 29:double)(children: CastLongToDouble(col 2:int) -> 28:double, CastLongToDouble(col 2:int) -> 29:double) -> 30:double - Statistics: Num rows: 2503 Data size: 209380 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col7), sum(_col6), count(_col1), sum(_col9), sum(_col8), count(_col2), sum(_col2), sum(_col3), count(_col3), sum(_col11), sum(_col10) - Group By Vectorization: - aggregators: VectorUDAFSumDouble(col 21:double) -> double, VectorUDAFSumDouble(col 18:double) -> double, VectorUDAFCount(col 1:smallint) -> bigint, VectorUDAFSumDouble(col 25:double) -> double, VectorUDAFSumDouble(col 22:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFSumDouble(col 26:double) -> double, VectorUDAFSumDouble(col 4:double) -> double, VectorUDAFCount(col 4:float) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFCount(col 2:int) -> bigint, VectorUDAFSumDouble(col 30:double) -> double, VectorUDAFSumDouble(col 27:double) -> double - className: VectorGroupByOperator - groupByMode: HASH - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: double), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: double), _col13 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), sum(VALUE._col9), sum(VALUE._col10), count(VALUE._col11), sum(VALUE._col12), sum(VALUE._col13) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D) (type: double), power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- power(((_col3 - ((_col4 * _col4) / _col5)) / _col5), 0.5)) (type: double), (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) % 79.553D) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) (type: double), power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5) (type: double), (- power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), _col9 (type: double), ((- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) * (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D))) / (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (- (power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5) - 10.175D)) (type: double), (UDFToDouble(_col10) / _col11) (type: double), (-3728.0D - power(((_col0 - ((_col1 * _col1) / _col2)) / CASE WHEN ((_col2 = 1L)) THEN (null) ELSE ((_col2 - 1)) END), 0.5)) (type: double), power(((_col12 - ((_col13 * _col13) / _col11)) / _col11), 0.5) (type: double), ((UDFToDouble(_col10) / _col11) / power(((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END), 0.5)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: SELECT STDDEV_SAMP(csmallint), - (STDDEV_SAMP(csmallint) - 10.175), - STDDEV_POP(ctinyint), - (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), - (-(STDDEV_POP(ctinyint))), - (STDDEV_SAMP(csmallint) % 79.553), - (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), - STDDEV_SAMP(cfloat), - (-(STDDEV_SAMP(csmallint))), - SUM(cfloat), - ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), - (-((STDDEV_SAMP(csmallint) - 10.175))), - AVG(cint), - (-3728 - STDDEV_SAMP(csmallint)), - STDDEV_POP(cint), - (AVG(cint) / STDDEV_SAMP(cfloat)) -FROM alltypesparquet -WHERE (((cint <= cfloat) - AND ((79.553 != cbigint) - AND (ctimestamp2 = -29071))) - OR ((cbigint > cdouble) - AND ((79.553 <= csmallint) - AND (ctimestamp1 > ctimestamp2)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT STDDEV_SAMP(csmallint), - (STDDEV_SAMP(csmallint) - 10.175), - STDDEV_POP(ctinyint), - (STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)), - (-(STDDEV_POP(ctinyint))), - (STDDEV_SAMP(csmallint) % 79.553), - (-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))), - STDDEV_SAMP(cfloat), - (-(STDDEV_SAMP(csmallint))), - SUM(cfloat), - ((-((STDDEV_SAMP(csmallint) * (STDDEV_SAMP(csmallint) - 10.175)))) / (STDDEV_SAMP(csmallint) - 10.175)), - (-((STDDEV_SAMP(csmallint) - 10.175))), - AVG(cint), - (-3728 - STDDEV_SAMP(csmallint)), - STDDEV_POP(cint), - (AVG(cint) / STDDEV_SAMP(cfloat)) -FROM alltypesparquet -WHERE (((cint <= cfloat) - AND ((79.553 != cbigint) - AND (ctimestamp2 = -29071))) - OR ((cbigint > cdouble) - AND ((79.553 <= csmallint) - AND (ctimestamp1 > ctimestamp2)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -0.0 -10.175 34.287285216637066 -0.0 -34.287285216637066 0.0 0.0 34.3469009551564 -0.0 197.89499950408936 -0.0 10.175 NULL -3728.0 NULL NULL diff --git ql/src/test/results/clientpositive/parquet_vectorization_4.q.out ql/src/test/results/clientpositive/parquet_vectorization_4.q.out deleted file mode 100644 index 4695b55e42..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_4.q.out +++ /dev/null @@ -1,194 +0,0 @@ -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT SUM(cint), - (SUM(cint) * -563), - (-3728 + SUM(cint)), - STDDEV_POP(cdouble), - (-(STDDEV_POP(cdouble))), - AVG(cdouble), - ((SUM(cint) * -563) % SUM(cint)), - (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), - VAR_POP(cdouble), - (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), - ((-3728 + SUM(cint)) - (SUM(cint) * -563)), - MIN(ctinyint), - MIN(ctinyint), - (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) -FROM alltypesparquet -WHERE (((csmallint >= cint) - OR ((-89010 >= ctinyint) - AND (cdouble > 79.553))) - OR ((-563 != cbigint) - AND ((ctinyint != cbigint) - OR (-3728 >= cdouble)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT SUM(cint), - (SUM(cint) * -563), - (-3728 + SUM(cint)), - STDDEV_POP(cdouble), - (-(STDDEV_POP(cdouble))), - AVG(cdouble), - ((SUM(cint) * -563) % SUM(cint)), - (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), - VAR_POP(cdouble), - (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), - ((-3728 + SUM(cint)) - (SUM(cint) * -563)), - MIN(ctinyint), - MIN(ctinyint), - (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) -FROM alltypesparquet -WHERE (((csmallint >= cint) - OR ((-89010 >= ctinyint) - AND (cdouble > 79.553))) - OR ((-563 != cbigint) - AND ((ctinyint != cbigint) - OR (-3728 >= cdouble)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((UDFToInteger(csmallint) >= cint) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or ((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterLongColGreaterEqualLongColumn(col 1:int, col 2:int)(children: col 1:smallint), FilterExprAndExpr(children: FilterLongColNotEqualLongScalar(col 3:bigint, val -563), FilterExprOrExpr(children: FilterLongColNotEqualLongColumn(col 0:bigint, col 3:bigint)(children: col 0:tinyint), FilterDoubleColLessEqualDoubleScalar(col 5:double, val -3728.0))), FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 0:int, val -89010)(children: col 0:tinyint), FilterDoubleColGreaterDoubleScalar(col 5:double, val 79.553))) - predicate: ((UDFToInteger(csmallint) >= cint) or ((cbigint <> -563L) and ((UDFToLong(ctinyint) <> cbigint) or (cdouble <= -3728.0D))) or ((UDFToInteger(ctinyint) <= -89010) and (cdouble > 79.553D))) (type: boolean) - Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cint (type: int), cdouble (type: double), ctinyint (type: tinyint), (cdouble * cdouble) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [2, 5, 0, 13] - selectExpressions: DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 13:double - Statistics: Num rows: 12288 Data size: 256884 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col0), sum(_col3), sum(_col1), count(_col1), min(_col2) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint, VectorUDAFMinLong(col 0:tinyint) -> tinyint - className: VectorGroupByOperator - groupByMode: HASH - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4] - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: tinyint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), min(VALUE._col4) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: bigint), (_col0 * -563L) (type: bigint), (-3728L + _col0) (type: bigint), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (- power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5)) (type: double), (_col2 / _col3) (type: double), ((_col0 * -563L) % _col0) (type: bigint), (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)) (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3))) (type: double), ((-3728L + _col0) - (_col0 * -563L)) (type: bigint), _col4 (type: tinyint), _col4 (type: tinyint), (UDFToDouble(_col4) * (- (UDFToDouble(((_col0 * -563L) % _col0)) / (_col2 / _col3)))) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT SUM(cint), - (SUM(cint) * -563), - (-3728 + SUM(cint)), - STDDEV_POP(cdouble), - (-(STDDEV_POP(cdouble))), - AVG(cdouble), - ((SUM(cint) * -563) % SUM(cint)), - (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), - VAR_POP(cdouble), - (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), - ((-3728 + SUM(cint)) - (SUM(cint) * -563)), - MIN(ctinyint), - MIN(ctinyint), - (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) -FROM alltypesparquet -WHERE (((csmallint >= cint) - OR ((-89010 >= ctinyint) - AND (cdouble > 79.553))) - OR ((-563 != cbigint) - AND ((ctinyint != cbigint) - OR (-3728 >= cdouble)))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT SUM(cint), - (SUM(cint) * -563), - (-3728 + SUM(cint)), - STDDEV_POP(cdouble), - (-(STDDEV_POP(cdouble))), - AVG(cdouble), - ((SUM(cint) * -563) % SUM(cint)), - (((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)), - VAR_POP(cdouble), - (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble)))), - ((-3728 + SUM(cint)) - (SUM(cint) * -563)), - MIN(ctinyint), - MIN(ctinyint), - (MIN(ctinyint) * (-((((SUM(cint) * -563) % SUM(cint)) / AVG(cdouble))))) -FROM alltypesparquet -WHERE (((csmallint >= cint) - OR ((-89010 >= ctinyint) - AND (cdouble > 79.553))) - OR ((-563 != cbigint) - AND ((ctinyint != cbigint) - OR (-3728 >= cdouble)))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --493101012745 277615870175435 -493101016473 136727.78682963562 -136727.78682963562 2298.5515807767374 0 0.0 1.8694487691330276E10 -0.0 -278108971191908 -64 -64 0.0 diff --git ql/src/test/results/clientpositive/parquet_vectorization_5.q.out ql/src/test/results/clientpositive/parquet_vectorization_5.q.out deleted file mode 100644 index ca09c45528..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_5.q.out +++ /dev/null @@ -1,181 +0,0 @@ -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT MAX(csmallint), - (MAX(csmallint) * -75), - COUNT(*), - ((MAX(csmallint) * -75) / COUNT(*)), - (6981 * MAX(csmallint)), - MIN(csmallint), - (-(MIN(csmallint))), - (197 % ((MAX(csmallint) * -75) / COUNT(*))), - SUM(cint), - MAX(ctinyint), - (-(MAX(ctinyint))), - ((-(MAX(ctinyint))) + MAX(ctinyint)) -FROM alltypesparquet -WHERE (((cboolean2 IS NOT NULL) - AND (cstring1 LIKE '%b%')) - OR ((ctinyint = cdouble) - AND ((ctimestamp2 IS NOT NULL) - AND (cstring2 LIKE 'a')))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT MAX(csmallint), - (MAX(csmallint) * -75), - COUNT(*), - ((MAX(csmallint) * -75) / COUNT(*)), - (6981 * MAX(csmallint)), - MIN(csmallint), - (-(MIN(csmallint))), - (197 % ((MAX(csmallint) * -75) / COUNT(*))), - SUM(cint), - MAX(ctinyint), - (-(MAX(ctinyint))), - ((-(MAX(ctinyint))) + MAX(ctinyint)) -FROM alltypesparquet -WHERE (((cboolean2 IS NOT NULL) - AND (cstring1 LIKE '%b%')) - OR ((ctinyint = cdouble) - AND ((ctimestamp2 IS NOT NULL) - AND (cstring2 LIKE 'a')))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cstring1 like '%b%') and cboolean2 is not null) or ((UDFToDouble(ctinyint) = cdouble) and (cstring2 like 'a') and ctimestamp2 is not null)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2330342 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6:string, pattern %b%), SelectColumnIsNotNull(col 11:boolean)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleColumn(col 13:double, col 5:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterStringColLikeStringScalar(col 7:string, pattern a), SelectColumnIsNotNull(col 9:timestamp))) - predicate: (((cstring1 like '%b%') and cboolean2 is not null) or ((UDFToDouble(ctinyint) = cdouble) and (cstring2 like 'a') and ctimestamp2 is not null)) (type: boolean) - Statistics: Num rows: 6879 Data size: 1304690 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) - outputColumnNames: ctinyint, csmallint, cint - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 6879 Data size: 1304690 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(csmallint), count(), min(csmallint), sum(cint), max(ctinyint) - Group By Vectorization: - aggregators: VectorUDAFMaxLong(col 1:smallint) -> smallint, VectorUDAFCountStar(*) -> bigint, VectorUDAFMinLong(col 1:smallint) -> smallint, VectorUDAFSumLong(col 2:int) -> bigint, VectorUDAFMaxLong(col 0:tinyint) -> tinyint - className: VectorGroupByOperator - groupByMode: HASH - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3, 4] - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: smallint), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: bigint), _col4 (type: tinyint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), count(VALUE._col1), min(VALUE._col2), sum(VALUE._col3), max(VALUE._col4) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: smallint), (UDFToInteger(_col0) * -75) (type: int), _col1 (type: bigint), (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1)) (type: double), (6981 * UDFToInteger(_col0)) (type: int), _col2 (type: smallint), (- _col2) (type: smallint), (197.0D % (UDFToDouble((UDFToInteger(_col0) * -75)) / UDFToDouble(_col1))) (type: double), _col3 (type: bigint), _col4 (type: tinyint), (- _col4) (type: tinyint), ((- _col4) + _col4) (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT MAX(csmallint), - (MAX(csmallint) * -75), - COUNT(*), - ((MAX(csmallint) * -75) / COUNT(*)), - (6981 * MAX(csmallint)), - MIN(csmallint), - (-(MIN(csmallint))), - (197 % ((MAX(csmallint) * -75) / COUNT(*))), - SUM(cint), - MAX(ctinyint), - (-(MAX(ctinyint))), - ((-(MAX(ctinyint))) + MAX(ctinyint)) -FROM alltypesparquet -WHERE (((cboolean2 IS NOT NULL) - AND (cstring1 LIKE '%b%')) - OR ((ctinyint = cdouble) - AND ((ctimestamp2 IS NOT NULL) - AND (cstring2 LIKE 'a')))) -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT MAX(csmallint), - (MAX(csmallint) * -75), - COUNT(*), - ((MAX(csmallint) * -75) / COUNT(*)), - (6981 * MAX(csmallint)), - MIN(csmallint), - (-(MIN(csmallint))), - (197 % ((MAX(csmallint) * -75) / COUNT(*))), - SUM(cint), - MAX(ctinyint), - (-(MAX(ctinyint))), - ((-(MAX(ctinyint))) + MAX(ctinyint)) -FROM alltypesparquet -WHERE (((cboolean2 IS NOT NULL) - AND (cstring1 LIKE '%b%')) - OR ((ctinyint = cdouble) - AND ((ctimestamp2 IS NOT NULL) - AND (cstring2 LIKE 'a')))) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -16343 -1225725 1070 -1145.53738317757 114090483 -16307 16307 197.0 -26853917571 11 -11 0 diff --git ql/src/test/results/clientpositive/parquet_vectorization_7.q.out ql/src/test/results/clientpositive/parquet_vectorization_7.q.out deleted file mode 100644 index 296fe106d5..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_7.q.out +++ /dev/null @@ -1,440 +0,0 @@ -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28815) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28815) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2770698 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28815.0)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) - predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28815.0D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 11033 Data size: 2487724 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] - selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 11033 Data size: 1754052 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) - null sort order: zzzzzzzzzzzzzzz - sort order: +++++++++++++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 11033 Data size: 1754052 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 11033 Data size: 1754052 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 25 - Statistics: Num rows: 25 Data size: 4180 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 25 Data size: 4180 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 25 - Processor Tree: - ListSink - -PREHOOK: query: SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28815) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28815) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -true NULL -15892 29 1969-12-31 15:59:57.937 821UdmGbkEf4j NULL -215 15892 -29 -12 NULL 171 -29 0 -true NULL -15899 50 1969-12-31 15:59:46.926 821UdmGbkEf4j NULL -222 15899 -50 -33 NULL 10210 -50 0 -true NULL -15903 -2 1969-12-31 15:59:46.371 cvLH6Eat2yFsyy7p NULL -226 15903 2 19 NULL 14465 2 0 -true NULL -15920 -64 1969-12-31 15:59:51.859 cvLH6Eat2yFsyy7p NULL -243 15920 64 81 NULL 6687 64 0 -true NULL -15922 -17 1969-12-31 15:59:46.164 821UdmGbkEf4j NULL -245 15922 17 34 NULL 10851 17 0 -true NULL -15923 49 1969-12-31 15:59:47.323 cvLH6Eat2yFsyy7p NULL -246 15923 -49 -32 NULL 2628 -49 0 -true NULL -15935 -6 1969-12-31 15:59:45.859 1cGVWH7n1QU NULL -1 15935 6 23 NULL 12046 6 0 -true NULL -15948 31 1969-12-31 15:59:47.577 821UdmGbkEf4j NULL -14 15948 -31 -14 NULL 7799 -31 0 -true NULL -15948 6 1969-12-31 15:59:49.269 1cGVWH7n1QU NULL -14 15948 -6 11 NULL 12436 -6 0 -true NULL -15980 -6 1969-12-31 15:59:54.84 1cGVWH7n1QU NULL -46 15980 6 23 NULL 14836 6 0 -true NULL -15999 4 1969-12-31 15:59:46.491 1cGVWH7n1QU NULL -65 15999 -4 13 NULL 1231 -4 0 -true NULL -16017 -21 1969-12-31 15:59:44.02 821UdmGbkEf4j NULL -83 16017 21 38 NULL 2282 21 0 -true NULL -16025 -42 1969-12-31 15:59:54.534 cvLH6Eat2yFsyy7p NULL -91 16025 42 59 NULL 14242 42 0 -true NULL -16036 -15 1969-12-31 15:59:58.681 1cGVWH7n1QU NULL -102 16036 15 32 NULL 7928 15 0 -true NULL -16059 -35 1969-12-31 15:59:53.038 821UdmGbkEf4j NULL -125 16059 35 52 NULL 12437 35 0 -true NULL -16076 59 1969-12-31 15:59:55.023 821UdmGbkEf4j NULL -142 16076 -59 -42 NULL 7907 -59 0 -true NULL -16122 50 1969-12-31 15:59:51.608 1cGVWH7n1QU NULL -188 16122 -50 -33 NULL 1828 -50 0 -true NULL -16123 -20 1969-12-31 15:59:51.177 1cGVWH7n1QU NULL -189 16123 20 37 NULL 2217 20 0 -true NULL -16153 35 1969-12-31 15:59:52.036 1cGVWH7n1QU NULL -219 16153 -35 -18 NULL 14817 -35 0 -true NULL -16169 5 1969-12-31 15:59:45.059 1cGVWH7n1QU NULL -235 16169 -5 12 NULL 6104 -5 0 -true NULL -16207 -4 1969-12-31 15:59:45.956 cvLH6Eat2yFsyy7p NULL -16 16207 4 21 NULL 8290 4 0 -true NULL -16221 -12 1969-12-31 15:59:45.877 1cGVWH7n1QU NULL -30 16221 12 29 NULL 1378 12 0 -true NULL -16227 2 1969-12-31 15:59:44.065 821UdmGbkEf4j NULL -36 16227 -2 15 NULL 9761 -2 0 -true NULL -16305 3 1969-12-31 15:59:43.878 1cGVWH7n1QU NULL -114 16305 -3 14 NULL 8491 -3 0 -true NULL -16339 15 1969-12-31 15:59:53.966 821UdmGbkEf4j NULL -148 16339 -15 2 NULL 12588 -15 0 -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800.0) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28792.3149999999999995) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800.0) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28792.3149999999999995) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2770698 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterDoubleColGreaterDoubleScalar(col 5:double, val 988888.0), FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 13:double, val -28792.315)(children: CastTimestampToDouble(col 9:timestamp) -> 13:double), FilterDoubleColLessEqualDoubleScalar(col 5:double, val 3569.0))), FilterExprOrExpr(children: FilterDoubleColLessEqualDoubleScalar(col 14:double, val -28800.0)(children: CastTimestampToDouble(col 8:timestamp) -> 14:double), FilterLongColEqualLongColumn(col 0:int, col 2:int)(children: col 0:tinyint), FilterStringColLikeStringScalar(col 7:string, pattern ss)), FilterLongColNotEqualLongScalar(col 0:tinyint, val 0)) - predicate: (((cdouble > 988888.0D) or ((UDFToDouble(ctimestamp2) > -28792.315D) and (cdouble <= 3569.0D))) and ((UDFToDouble(ctimestamp1) <= -28800.0D) or (UDFToInteger(ctinyint) = cint) or (cstring2 like 'ss')) and (ctinyint <> 0Y)) (type: boolean) - Statistics: Num rows: 11033 Data size: 2487724 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cboolean1 (type: boolean), cbigint (type: bigint), csmallint (type: smallint), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cstring1 (type: string), (cbigint + cbigint) (type: bigint), (UDFToInteger(csmallint) % -257) (type: int), (- csmallint) (type: smallint), (- ctinyint) (type: tinyint), (UDFToInteger((- ctinyint)) + 17) (type: int), (cbigint * UDFToLong((- csmallint))) (type: bigint), (cint % UDFToInteger(csmallint)) (type: int), (- ctinyint) (type: tinyint), ((- ctinyint) % ctinyint) (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [10, 3, 1, 0, 8, 6, 15, 16, 17, 18, 20, 22, 23, 24, 26] - selectExpressions: LongColAddLongColumn(col 3:bigint, col 3:bigint) -> 15:bigint, LongColModuloLongScalar(col 1:int, val -257)(children: col 1:smallint) -> 16:int, LongColUnaryMinus(col 1:smallint) -> 17:smallint, LongColUnaryMinus(col 0:tinyint) -> 18:tinyint, LongColAddLongScalar(col 19:int, val 17)(children: LongColUnaryMinus(col 0:tinyint) -> 19:tinyint) -> 20:int, LongColMultiplyLongColumn(col 3:bigint, col 21:bigint)(children: LongColUnaryMinus(col 1:smallint) -> 21:smallint) -> 22:bigint, LongColModuloLongColumn(col 2:int, col 1:int)(children: col 1:smallint) -> 23:int, LongColUnaryMinus(col 0:tinyint) -> 24:tinyint, LongColModuloLongColumn(col 25:tinyint, col 0:tinyint)(children: LongColUnaryMinus(col 0:tinyint) -> 25:tinyint) -> 26:tinyint - Statistics: Num rows: 11033 Data size: 1754052 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint) - null sort order: zzzzzzzzzzzzzzz - sort order: +++++++++++++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 11033 Data size: 1754052 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: boolean), KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey2 (type: smallint), KEY.reducesinkkey3 (type: tinyint), KEY.reducesinkkey4 (type: timestamp), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey6 (type: bigint), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: smallint), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey10 (type: int), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: int), KEY.reducesinkkey9 (type: tinyint), KEY.reducesinkkey14 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 - Statistics: Num rows: 11033 Data size: 1754052 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 25 - Statistics: Num rows: 25 Data size: 4180 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 25 Data size: 4180 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 25 - Processor Tree: - ListSink - -PREHOOK: query: SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800.0) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28792.3149999999999995) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT cboolean1, - cbigint, - csmallint, - ctinyint, - ctimestamp1, - cstring1, - (cbigint + cbigint) as c1, - (csmallint % -257) as c2, - (-(csmallint)) as c3, - (-(ctinyint)) as c4, - ((-(ctinyint)) + 17) as c5, - (cbigint * (-(csmallint))) as c6, - (cint % csmallint) as c7, - (-(ctinyint)) as c8, - ((-(ctinyint)) % ctinyint) as c9 -FROM alltypesparquet -WHERE ((ctinyint != 0) - AND (((ctimestamp1 <= -28800.0) - OR ((ctinyint = cint) - OR (cstring2 LIKE 'ss'))) - AND ((988888 < cdouble) - OR ((ctimestamp2 > -28792.3149999999999995) - AND (3569 >= cdouble))))) -ORDER BY cboolean1, cbigint, csmallint, ctinyint, ctimestamp1, cstring1, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -true NULL -14584 -7 1969-12-31 15:59:46.965 1cGVWH7n1QU NULL -192 14584 7 24 NULL 5864 7 0 -true NULL -14739 4 1969-12-31 15:59:55.188 cvLH6Eat2yFsyy7p NULL -90 14739 -4 13 NULL 8966 -4 0 -true NULL -14771 13 1969-12-31 15:59:58.839 821UdmGbkEf4j NULL -122 14771 -13 4 NULL 12897 -13 0 -true NULL -15149 20 1969-12-31 15:59:46.575 1cGVWH7n1QU NULL -243 15149 -20 -3 NULL 10520 -20 0 -true NULL -15344 48 1969-12-31 15:59:54.853 821UdmGbkEf4j NULL -181 15344 -48 -31 NULL 13871 -48 0 -true NULL -15388 49 1969-12-31 15:59:58.545 cvLH6Eat2yFsyy7p NULL -225 15388 -49 -32 NULL 3131 -49 0 -true NULL -15431 -11 1969-12-31 15:59:52.176 cvLH6Eat2yFsyy7p NULL -11 15431 11 28 NULL 7586 11 0 -true NULL -15435 -21 1969-12-31 15:59:54.705 1cGVWH7n1QU NULL -15 15435 21 38 NULL 6586 21 0 -true NULL -15450 -34 1969-12-31 15:59:55.681 cvLH6Eat2yFsyy7p NULL -30 15450 34 51 NULL 5717 34 0 -true NULL -15478 7 1969-12-31 15:59:56.809 cvLH6Eat2yFsyy7p NULL -58 15478 -7 10 NULL 7501 -7 0 -true NULL -15555 -2 1969-12-31 15:59:58.773 1cGVWH7n1QU NULL -135 15555 2 19 NULL 9991 2 0 -true NULL -15659 -11 1969-12-31 15:59:48.466 cvLH6Eat2yFsyy7p NULL -239 15659 11 28 NULL 12199 11 0 -true NULL -15711 -60 1969-12-31 15:59:53.115 821UdmGbkEf4j NULL -34 15711 60 77 NULL 7646 60 0 -true NULL -15770 -23 1969-12-31 15:59:56.822 1cGVWH7n1QU NULL -93 15770 23 40 NULL 4926 23 0 -true NULL -15794 53 1969-12-31 15:59:53.749 cvLH6Eat2yFsyy7p NULL -117 15794 -53 -36 NULL 4351 -53 0 -true NULL -15892 29 1969-12-31 15:59:57.937 821UdmGbkEf4j NULL -215 15892 -29 -12 NULL 171 -29 0 -true NULL -15899 50 1969-12-31 15:59:46.926 821UdmGbkEf4j NULL -222 15899 -50 -33 NULL 10210 -50 0 -true NULL -15920 -64 1969-12-31 15:59:51.859 cvLH6Eat2yFsyy7p NULL -243 15920 64 81 NULL 6687 64 0 -true NULL -15922 -17 1969-12-31 15:59:46.164 821UdmGbkEf4j NULL -245 15922 17 34 NULL 10851 17 0 -true NULL -15980 -6 1969-12-31 15:59:54.84 1cGVWH7n1QU NULL -46 15980 6 23 NULL 14836 6 0 -true NULL -16017 -21 1969-12-31 15:59:44.02 821UdmGbkEf4j NULL -83 16017 21 38 NULL 2282 21 0 -true NULL -16036 -15 1969-12-31 15:59:58.681 1cGVWH7n1QU NULL -102 16036 15 32 NULL 7928 15 0 -true NULL -16076 59 1969-12-31 15:59:55.023 821UdmGbkEf4j NULL -142 16076 -59 -42 NULL 7907 -59 0 -true NULL -16122 50 1969-12-31 15:59:51.608 1cGVWH7n1QU NULL -188 16122 -50 -33 NULL 1828 -50 0 -true NULL -16153 35 1969-12-31 15:59:52.036 1cGVWH7n1QU NULL -219 16153 -35 -18 NULL 14817 -35 0 diff --git ql/src/test/results/clientpositive/parquet_vectorization_8.q.out ql/src/test/results/clientpositive/parquet_vectorization_8.q.out deleted file mode 100644 index 697e50bedb..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_8.q.out +++ /dev/null @@ -1,414 +0,0 @@ -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 10) - AND (ctimestamp2 != 16))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 10) - AND (ctimestamp2 != 16))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2733998 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 10.0)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val 16.0)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), SelectColumnIsNotNull(col 7:string)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0), SelectColumnIsNotNull(col 10:boolean))) - predicate: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 10.0D) and (UDFToDouble(ctimestamp2) <> 16.0D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) - Statistics: Num rows: 3059 Data size: 680930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [8, 5, 10, 6, 4, 15, 16, 17, 19, 22, 23, 24, 25, 29] - selectExpressions: DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 16:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 17:double, DoubleColAddDoubleColumn(col 18:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 18:float) -> 19:float, DoubleColAddDoubleColumn(col 20:double, col 21:double)(children: DoubleColUnaryMinus(col 5:double) -> 20:double, CastLongToDouble(col 3:bigint) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 5:double) -> 23:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 24:float, DoubleColUnaryMinus(col 4:float) -> 25:float, DoubleColAddDoubleColumn(col 26:double, col 28:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 26:double, DoubleColAddDoubleColumn(col 27:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 27:float) -> 28:float) -> 29:double - Statistics: Num rows: 3059 Data size: 526290 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) - null sort order: zzzzzzzzzzzzzz - sort order: ++++++++++++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3059 Data size: 526290 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 3059 Data size: 526290 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 3600 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 3600 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 10) - AND (ctimestamp2 != 16))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 10) - AND (ctimestamp2 != 16))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -1969-12-31 15:59:30.929 -200.0 NULL NULL 12.0 200.0 -5438.15 51400.0 NULL 2.128824065E9 200.0 -13.389 -12.0 NULL -1969-12-31 15:59:30.929 -200.0 NULL NULL 42.0 200.0 -5438.15 51400.0 NULL -5.78935585E8 200.0 -43.389 -42.0 NULL -1969-12-31 15:59:30.929 -7196.0 NULL NULL 49.0 7196.0 1557.8500000000004 1849372.0 NULL 1.948230809E9 7196.0 -50.389 -49.0 NULL -1969-12-31 15:59:30.929 15601.0 NULL NULL -54.0 -15601.0 -21239.15 -4009457.0 NULL -1.114185408E9 -15601.0 52.611 54.0 NULL -1969-12-31 15:59:43.628 -200.0 NULL NULL 23.0 200.0 -5438.15 51400.0 NULL 2.034056161E9 200.0 -24.389 -23.0 NULL -1969-12-31 15:59:43.637 -7196.0 NULL NULL -44.0 7196.0 1557.8500000000004 1849372.0 NULL 1.100301451E9 7196.0 42.611 44.0 NULL -1969-12-31 15:59:43.64 -7196.0 NULL NULL -51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.339157623E9 7196.0 49.611 51.0 NULL -1969-12-31 15:59:43.661 -200.0 NULL NULL 13.0 200.0 -5438.15 51400.0 NULL -6.8063459E7 200.0 -14.389 -13.0 NULL -1969-12-31 15:59:43.676 -200.0 NULL NULL -10.0 200.0 -5438.15 51400.0 NULL 8.34296111E8 200.0 8.611 10.0 NULL -1969-12-31 15:59:43.705 15601.0 NULL NULL -12.0 -15601.0 -21239.15 -4009457.0 NULL 5.95398978E8 -15601.0 10.611 12.0 NULL -1969-12-31 15:59:43.709 15601.0 NULL NULL 61.0 -15601.0 -21239.15 -4009457.0 NULL -1.55652257E8 -15601.0 -62.389 -61.0 NULL -1969-12-31 15:59:43.72 -200.0 NULL NULL -18.0 200.0 -5438.15 51400.0 NULL 1.809037075E9 200.0 16.611 18.0 NULL -1969-12-31 15:59:43.721 15601.0 NULL NULL 57.0 -15601.0 -21239.15 -4009457.0 NULL -1.465672807E9 -15601.0 -58.389 -57.0 NULL -1969-12-31 15:59:43.749 -7196.0 NULL NULL -39.0 7196.0 1557.8500000000004 1849372.0 NULL 3.96436076E8 7196.0 37.611 39.0 NULL -1969-12-31 15:59:43.771 15601.0 NULL NULL 49.0 -15601.0 -21239.15 -4009457.0 NULL -1.10733693E9 -15601.0 -50.389 -49.0 NULL -1969-12-31 15:59:43.773 -200.0 NULL NULL -24.0 200.0 -5438.15 51400.0 NULL -1.046049502E9 200.0 22.611 24.0 NULL -1969-12-31 15:59:43.782 -7196.0 NULL NULL 51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.607339819E9 7196.0 -52.389 -51.0 NULL -1969-12-31 15:59:43.783 -200.0 NULL NULL -11.0 200.0 -5438.15 51400.0 NULL 1.2116287E7 200.0 9.611 11.0 NULL -1969-12-31 15:59:43.807 -7196.0 NULL NULL 42.0 7196.0 1557.8500000000004 1849372.0 NULL -5.98226333E8 7196.0 -43.389 -42.0 NULL -1969-12-31 15:59:43.82 -7196.0 NULL NULL -30.0 7196.0 1557.8500000000004 1849372.0 NULL 1.329550715E9 7196.0 28.611 30.0 NULL -PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 12.503) - AND (ctimestamp2 != 11.998))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION -SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 12.503) - AND (ctimestamp2 != 11.998))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) - Statistics: Num rows: 12288 Data size: 2733998 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterExprOrExpr(children: FilterDoubleColLessDoubleScalar(col 4:float, val -6432.0), FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleScalar(col 13:double, val 12.503)(children: CastTimestampToDouble(col 8:timestamp) -> 13:double), FilterDoubleColNotEqualDoubleScalar(col 14:double, val 11.998)(children: CastTimestampToDouble(col 9:timestamp) -> 14:double), SelectColumnIsNotNull(col 7:string)), FilterExprAndExpr(children: FilterDoubleColEqualDoubleScalar(col 5:double, val 988888.0), SelectColumnIsNotNull(col 10:boolean))) - predicate: ((cfloat < -6432.0) or ((UDFToDouble(ctimestamp1) <= 12.503D) and (UDFToDouble(ctimestamp2) <> 11.998D) and cstring2 is not null) or ((cdouble = 988888.0D) and cboolean1 is not null)) (type: boolean) - Statistics: Num rows: 3059 Data size: 680930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctimestamp1 (type: timestamp), cdouble (type: double), cboolean1 (type: boolean), cstring1 (type: string), cfloat (type: float), (- cdouble) (type: double), (-5638.15D - cdouble) (type: double), (cdouble * -257.0D) (type: double), (UDFToFloat(cint) + cfloat) (type: float), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (- cdouble) (type: double), (-1.389 - cfloat) (type: float), (- cfloat) (type: float), ((-5638.15D - cdouble) + UDFToDouble((UDFToFloat(cint) + cfloat))) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [8, 5, 10, 6, 4, 15, 16, 17, 19, 22, 23, 24, 25, 29] - selectExpressions: DoubleColUnaryMinus(col 5:double) -> 15:double, DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 16:double, DoubleColMultiplyDoubleScalar(col 5:double, val -257.0) -> 17:double, DoubleColAddDoubleColumn(col 18:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 18:float) -> 19:float, DoubleColAddDoubleColumn(col 20:double, col 21:double)(children: DoubleColUnaryMinus(col 5:double) -> 20:double, CastLongToDouble(col 3:bigint) -> 21:double) -> 22:double, DoubleColUnaryMinus(col 5:double) -> 23:double, DoubleScalarSubtractDoubleColumn(val -1.3890000581741333, col 4:float) -> 24:float, DoubleColUnaryMinus(col 4:float) -> 25:float, DoubleColAddDoubleColumn(col 26:double, col 28:double)(children: DoubleScalarSubtractDoubleColumn(val -5638.15, col 5:double) -> 26:double, DoubleColAddDoubleColumn(col 27:float, col 4:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 27:float) -> 28:float) -> 29:double - Statistics: Num rows: 3059 Data size: 526290 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double) - null sort order: zzzzzzzzzzzzzz - sort order: ++++++++++++++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 3059 Data size: 526290 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: boolean), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: float), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double), KEY.reducesinkkey8 (type: float), KEY.reducesinkkey9 (type: double), KEY.reducesinkkey5 (type: double), KEY.reducesinkkey11 (type: float), KEY.reducesinkkey12 (type: float), KEY.reducesinkkey13 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 - Statistics: Num rows: 3059 Data size: 526290 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 3600 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 3600 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 12.503) - AND (ctimestamp2 != 11.998))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT ctimestamp1, - cdouble, - cboolean1, - cstring1, - cfloat, - (-(cdouble)) as c1, - (-5638.15 - cdouble) as c2, - (cdouble * -257) as c3, - (cint + cfloat) as c4, - ((-(cdouble)) + cbigint) as c5, - (-(cdouble)) as c6, - (-1.389 - cfloat) as c7, - (-(cfloat)) as c8, - ((-5638.15 - cdouble) + (cint + cfloat)) as c9 -FROM alltypesparquet -WHERE (((cstring2 IS NOT NULL) - AND ((ctimestamp1 <= 12.503) - AND (ctimestamp2 != 11.998))) - OR ((cfloat < -6432) - OR ((cboolean1 IS NOT NULL) - AND (cdouble = 988888)))) -ORDER BY ctimestamp1, cdouble, cboolean1, cstring1, cfloat, c1, c2, c3, c4, c5, c6, c7, c8, c9 -LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -1969-12-31 15:59:30.929 -200.0 NULL NULL 12.0 200.0 -5438.15 51400.0 NULL 2.128824065E9 200.0 -13.389 -12.0 NULL -1969-12-31 15:59:30.929 -200.0 NULL NULL 42.0 200.0 -5438.15 51400.0 NULL -5.78935585E8 200.0 -43.389 -42.0 NULL -1969-12-31 15:59:30.929 -7196.0 NULL NULL 49.0 7196.0 1557.8500000000004 1849372.0 NULL 1.948230809E9 7196.0 -50.389 -49.0 NULL -1969-12-31 15:59:30.929 15601.0 NULL NULL -54.0 -15601.0 -21239.15 -4009457.0 NULL -1.114185408E9 -15601.0 52.611 54.0 NULL -1969-12-31 15:59:43.628 -200.0 NULL NULL 23.0 200.0 -5438.15 51400.0 NULL 2.034056161E9 200.0 -24.389 -23.0 NULL -1969-12-31 15:59:43.637 -7196.0 NULL NULL -44.0 7196.0 1557.8500000000004 1849372.0 NULL 1.100301451E9 7196.0 42.611 44.0 NULL -1969-12-31 15:59:43.64 -7196.0 NULL NULL -51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.339157623E9 7196.0 49.611 51.0 NULL -1969-12-31 15:59:43.661 -200.0 NULL NULL 13.0 200.0 -5438.15 51400.0 NULL -6.8063459E7 200.0 -14.389 -13.0 NULL -1969-12-31 15:59:43.676 -200.0 NULL NULL -10.0 200.0 -5438.15 51400.0 NULL 8.34296111E8 200.0 8.611 10.0 NULL -1969-12-31 15:59:43.705 15601.0 NULL NULL -12.0 -15601.0 -21239.15 -4009457.0 NULL 5.95398978E8 -15601.0 10.611 12.0 NULL -1969-12-31 15:59:43.709 15601.0 NULL NULL 61.0 -15601.0 -21239.15 -4009457.0 NULL -1.55652257E8 -15601.0 -62.389 -61.0 NULL -1969-12-31 15:59:43.72 -200.0 NULL NULL -18.0 200.0 -5438.15 51400.0 NULL 1.809037075E9 200.0 16.611 18.0 NULL -1969-12-31 15:59:43.721 15601.0 NULL NULL 57.0 -15601.0 -21239.15 -4009457.0 NULL -1.465672807E9 -15601.0 -58.389 -57.0 NULL -1969-12-31 15:59:43.749 -7196.0 NULL NULL -39.0 7196.0 1557.8500000000004 1849372.0 NULL 3.96436076E8 7196.0 37.611 39.0 NULL -1969-12-31 15:59:43.771 15601.0 NULL NULL 49.0 -15601.0 -21239.15 -4009457.0 NULL -1.10733693E9 -15601.0 -50.389 -49.0 NULL -1969-12-31 15:59:43.773 -200.0 NULL NULL -24.0 200.0 -5438.15 51400.0 NULL -1.046049502E9 200.0 22.611 24.0 NULL -1969-12-31 15:59:43.782 -7196.0 NULL NULL 51.0 7196.0 1557.8500000000004 1849372.0 NULL -1.607339819E9 7196.0 -52.389 -51.0 NULL -1969-12-31 15:59:43.783 -200.0 NULL NULL -11.0 200.0 -5438.15 51400.0 NULL 1.2116287E7 200.0 9.611 11.0 NULL -1969-12-31 15:59:43.807 -7196.0 NULL NULL 42.0 7196.0 1557.8500000000004 1849372.0 NULL -5.98226333E8 7196.0 -43.389 -42.0 NULL -1969-12-31 15:59:43.82 -7196.0 NULL NULL -30.0 7196.0 1557.8500000000004 1849372.0 NULL 1.329550715E9 7196.0 28.611 30.0 NULL diff --git ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out deleted file mode 100644 index 1cdecf164a..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_limit.q.out +++ /dev/null @@ -1,785 +0,0 @@ -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cbigint (type: bigint), cdouble (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 7 - Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - - Stage: Stage-0 - Fetch Operator - limit: 7 - Processor Tree: - ListSink - -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 7 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --1887561756 -10011.0 --1887561756 -13877.0 --1887561756 -2281.0 --1887561756 -8881.0 --1887561756 10361.0 --1887561756 1839.0 --1887561756 9531.0 -PREHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:tinyint) - predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: double) - null sort order: zz - sort order: ++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col2 (type: smallint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --64 -10462.0 -10462 --64 -15920.0 -15920 --64 -1600.0 -1600 --64 -200.0 -200 --64 -2919.0 -2919 --64 -3097.0 -3097 --64 -3586.0 -3586 --64 -4018.0 -4018 --64 -4040.0 -4040 --64 -4803.0 -4803 --64 -6907.0 -6907 --64 -7196.0 -7196 --64 -7196.0 -7196 --64 -7196.0 -7196 --64 -7196.0 -7196 --64 -7196.0 -7196 --64 -7196.0 -7196 --64 -7196.0 -7196 --64 -8080.0 -8080 --64 -9842.0 -9842 -PREHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Select Operator - expressions: ctinyint (type: tinyint), (cdouble + 1.0D) (type: double) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 13] - selectExpressions: DoubleColAddDoubleScalar(col 5:double, val 1.0) -> 13:double - Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1), count(_col1) - Group By Vectorization: - aggregators: VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFCount(col 13:double) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:tinyint - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1] - keys: _col0 (type: tinyint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: tinyint) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: tinyint) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: double), _col2 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: tinyint) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 131 Data size: 2492 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: tinyint), (_col1 / _col2) (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: select ctinyint,avg(cdouble + 1) from alltypesparquet group by ctinyint order by ctinyint limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --45 326.44444444444446 --46 3033.55 --47 -574.6428571428571 --48 1672.909090909091 --49 768.7659574468086 --50 -960.0192307692307 --51 -96.46341463414635 --52 2810.705882352941 --53 -532.7567567567568 --54 2712.7272727272725 --55 2385.595744680851 --56 2595.818181818182 --57 1867.0535714285713 --58 3483.2444444444445 --59 318.27272727272725 --60 1071.82 --61 914.3404255319149 --62 245.69387755102042 --63 2178.7272727272725 --64 373.52941176470586 -PREHOOK: query: explain VECTORIZATION EXPRESSION -select distinct(ctinyint) from alltypesparquet limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain VECTORIZATION EXPRESSION -select distinct(ctinyint) from alltypesparquet limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Select Operator - expressions: ctinyint (type: tinyint) - outputColumnNames: ctinyint - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0] - Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - Group By Vectorization: - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:tinyint - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [] - keys: ctinyint (type: tinyint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: tinyint) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: tinyint) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: tinyint) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 131 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: select distinct(ctinyint) from alltypesparquet limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: select distinct(ctinyint) from alltypesparquet limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --45 --46 --47 --48 --49 --50 --51 --52 --53 --54 --55 --56 --57 --58 --59 --60 --61 --62 --63 --64 -PREHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Select Operator - expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: ctinyint, cdouble - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 5] - Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(DISTINCT cdouble) - Group By Vectorization: - aggregators: VectorUDAFCount(col 5:double) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:tinyint, col 5:double - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] - keys: ctinyint (type: tinyint), cdouble (type: double) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6144 Data size: 104204 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: double) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: tinyint) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, No DISTINCT columns IS false - Statistics: Num rows: 6144 Data size: 104204 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: count(DISTINCT KEY._col1:0._col0) - keys: KEY._col0 (type: tinyint) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 131 Data size: 1444 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesparquet group by ctinyint order by ctinyint limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --45 24 --46 24 --47 22 --48 29 --49 26 --50 30 --51 21 --52 33 --53 22 --54 26 --55 29 --56 36 --57 35 --58 23 --59 31 --60 27 --61 25 --62 27 --63 19 --64 24 -PREHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain VECTORIZATION EXPRESSION -select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 0 - Processor Tree: - ListSink - -PREHOOK: query: select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: select ctinyint,cdouble from alltypesparquet order by ctinyint limit 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PREHOOK: query: explain VECTORIZATION EXPRESSION -select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain VECTORIZATION EXPRESSION -select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 110096 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:tinyint) - predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(ctinyint) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0:tinyint) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 5:double - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] - keys: cdouble (type: double) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: double) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: double) - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: double) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - Reduce Output Operator - key expressions: _col1 (type: bigint), _col0 (type: double) - null sort order: zz - sort order: ++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4586 Data size: 64088 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 20 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: select cdouble, sum(ctinyint) as sum from alltypesparquet where ctinyint is not null group by cdouble order by sum, cdouble limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --10462.0 -64 --1121.0 -89 --11322.0 -101 --11492.0 -78 --15920.0 -64 --4803.0 -64 --6907.0 -64 --7196.0 -2009 --8080.0 -64 --8118.0 -80 --9842.0 -64 -10496.0 -67 -15601.0 -1733 -3520.0 -86 -4811.0 -115 -5241.0 -80 -557.0 -75 -7705.0 -88 -9452.0 -76 -NULL -32768 diff --git ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out deleted file mode 100644 index 9bd884513b..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_offset_limit.q.out +++ /dev/null @@ -1,174 +0,0 @@ -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 12288 Data size: 183488 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((cint > 0) and (UDFToDouble(cbigint) < cdouble)) (type: boolean) - Statistics: Num rows: 2048 Data size: 30600 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cbigint (type: bigint), cdouble (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2048 Data size: 24480 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 2 - Offset of rows: 3 - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - - Stage: Stage-0 - Fetch Operator - limit: 2 - Processor Tree: - ListSink - -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT cbigint, cdouble FROM alltypesparquet WHERE cbigint < cdouble and cint > 0 limit 3,2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --1887561756 10361.0 --1887561756 -8881.0 -PREHOOK: query: explain vectorization expression -select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization expression -select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: ctinyint is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 146796 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:tinyint) - predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ctinyint (type: tinyint), cdouble (type: double), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 5, 1] - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: double) - null sort order: zz - sort order: ++ - Reduce Sink Vectorization: - className: VectorReduceSinkOperator - native: false - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: smallint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Offset of rows: 10 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - ListSink - -PREHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: select ctinyint,cdouble,csmallint from alltypesparquet where ctinyint is not null order by ctinyint,cdouble limit 10,3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --64 -7196.0 -7196 --64 -6907.0 -6907 --64 -4803.0 -4803 diff --git ql/src/test/results/clientpositive/parquet_vectorization_pushdown.q.out ql/src/test/results/clientpositive/parquet_vectorization_pushdown.q.out deleted file mode 100644 index e129666228..0000000000 --- ql/src/test/results/clientpositive/parquet_vectorization_pushdown.q.out +++ /dev/null @@ -1,91 +0,0 @@ -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: explain vectorization SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alltypesparquet - filterExpr: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 12288 Data size: 146792 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(cbigint) < cdouble) (type: boolean) - Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: cbigint (type: bigint) - outputColumnNames: cbigint - Statistics: Num rows: 4096 Data size: 48944 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(cbigint), count(cbigint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToDouble(_col0) / _col1) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -WARNING: Comparing a bigint and a double may result in a loss of precision. -PREHOOK: query: SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### -POSTHOOK: query: SELECT AVG(cbigint) FROM alltypesparquet WHERE cbigint < cdouble -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesparquet -#### A masked pattern was here #### --1.4670720493864927E9 diff --git ql/src/test/results/clientpositive/partition_boolexpr.q.out ql/src/test/results/clientpositive/partition_boolexpr.q.out deleted file mode 100644 index 4ecc6b7ab6..0000000000 --- ql/src/test/results/clientpositive/partition_boolexpr.q.out +++ /dev/null @@ -1,289 +0,0 @@ -PREHOOK: query: create table part_boolexpr(key int, value string) partitioned by (dt int, ts string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@part_boolexpr -POSTHOOK: query: create table part_boolexpr(key int, value string) partitioned by (dt int, ts string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@part_boolexpr -PREHOOK: query: select count(*) from part_boolexpr where key = 'abc' -PREHOOK: type: QUERY -PREHOOK: Input: default@part_boolexpr -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from part_boolexpr where key = 'abc' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part_boolexpr -#### A masked pattern was here #### -0 -PREHOOK: query: select * from part_boolexpr where dt = 'abc' -PREHOOK: type: QUERY -PREHOOK: Input: default@part_boolexpr -#### A masked pattern was here #### -POSTHOOK: query: select * from part_boolexpr where dt = 'abc' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part_boolexpr -#### A masked pattern was here #### -PREHOOK: query: explain select count(1) from srcpart where true -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -#### A masked pattern was here #### -POSTHOOK: query: explain select count(1) from srcpart where true -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 1 - Processor Tree: - ListSink - -PREHOOK: query: explain select count(1) from srcpart where false -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: explain select count(1) from srcpart where false -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select count(1) from srcpart where true and hr='11' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -#### A masked pattern was here #### -POSTHOOK: query: explain select count(1) from srcpart where true and hr='11' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 1 - Processor Tree: - ListSink - -PREHOOK: query: explain select count(1) from srcpart where true or hr='11' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -#### A masked pattern was here #### -POSTHOOK: query: explain select count(1) from srcpart where true or hr='11' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 1 - Processor Tree: - ListSink - -PREHOOK: query: explain select count(1) from srcpart where false or hr='11' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -#### A masked pattern was here #### -POSTHOOK: query: explain select count(1) from srcpart where false or hr='11' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 1 - Processor Tree: - ListSink - -PREHOOK: query: explain select count(1) from srcpart where false and hr='11' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: explain select count(1) from srcpart where false and hr='11' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select count(1) from srcpart where INPUT__FILE__NAME is not null -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: explain select count(1) from srcpart where INPUT__FILE__NAME is not null -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: INPUT__FILE__NAME is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: INPUT__FILE__NAME is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 2000 Data size: 37248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/pcr.q.out ql/src/test/results/clientpositive/pcr.q.out deleted file mode 100644 index cf6f1b0b67..0000000000 --- ql/src/test/results/clientpositive/pcr.q.out +++ /dev/null @@ -1,5881 +0,0 @@ -PREHOOK: query: drop table pcr_t1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table pcr_t2 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t2 -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table pcr_t3 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t3 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_t1 -POSTHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_t1 -PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-08') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1@ds=2000-04-08 -POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-08') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-09') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1@ds=2000-04-09 -POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-09') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-10') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1@ds=2000-04-10 -POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-10') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1@ds=2000-04-10 -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE `key` < 5 AND `ds` <= '2000-04-09' -ORDER BY `key`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: ((key < 5) and (ds <= '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key < 5) (type: boolean) - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -0 val_0 2000-04-08 -0 val_0 2000-04-08 -0 val_0 2000-04-08 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -2 val_2 2000-04-08 -2 val_2 2000-04-09 -4 val_4 2000-04-08 -4 val_4 2000-04-09 -PREHOOK: query: explain extended select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value` -FROM `default`.`pcr_t1` -WHERE `key` < 5 OR `ds` <= '2000-04-09' -ORDER BY `key` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: ((key < 5) or (ds <= '2000-04-09')) (type: boolean) - Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key < 5) or (ds <= '2000-04-09')) (type: boolean) - Statistics: Num rows: 36 Data size: 10008 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 36 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select key, value from pcr_t1 where ds<='2000-04-09' or key<5 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -2 val_2 -2 val_2 -2 val_2 -4 val_4 -4 val_4 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -8 val_8 -9 val_9 -9 val_9 -10 val_10 -10 val_10 -11 val_11 -11 val_11 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -17 val_17 -17 val_17 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -19 val_19 -19 val_19 -PREHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE `key` < 5 AND `value` <> 'val_2' AND `ds` <= '2000-04-09' -ORDER BY `key`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: ((key < 5) and (value <> 'val_2')) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key < 5) and (value <> 'val_2')) (type: boolean) - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 11 Data size: 3058 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 where ds<='2000-04-09' and key<5 and value != 'val_2' order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -0 val_0 2000-04-08 -0 val_0 2000-04-08 -0 val_0 2000-04-08 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -4 val_4 2000-04-08 -4 val_4 2000-04-09 -PREHOOK: query: explain extended -select key, value, ds from pcr_t1 -where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds from pcr_t1 -where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE `ds` < '2000-04-09' AND `key` < 5 OR `ds` > '2000-04-09' AND `value` = 'val_5' -ORDER BY `key`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds < '2000-04-09') and (key < 5)) or ((ds > '2000-04-09') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 4 Data size: 1112 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 -where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 -where (ds < '2000-04-09' and key < 5) or (ds > '2000-04-09' and value == 'val_5') order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -0 val_0 2000-04-08 -0 val_0 2000-04-08 -0 val_0 2000-04-08 -2 val_2 2000-04-08 -4 val_4 2000-04-08 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -PREHOOK: query: explain extended -select key, value, ds from pcr_t1 -where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds from pcr_t1 -where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE `ds` < '2000-04-10' AND `key` < 5 OR `ds` > '2000-04-08' AND `value` = 'val_5' -ORDER BY `key`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds < '2000-04-10') and (key < 5)) or ((ds > '2000-04-08') and (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 7 Data size: 1946 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 -where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 -where (ds < '2000-04-10' and key < 5) or (ds > '2000-04-08' and value == 'val_5') order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -0 val_0 2000-04-08 -0 val_0 2000-04-08 -0 val_0 2000-04-08 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -2 val_2 2000-04-08 -2 val_2 2000-04-09 -4 val_4 2000-04-08 -4 val_4 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -PREHOOK: query: explain extended -select key, value, ds from pcr_t1 -where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds from pcr_t1 -where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE (`ds` < '2000-04-10' OR `key` < 5) AND (`ds` > '2000-04-08' OR `value` = 'val_5') -ORDER BY `key`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds < '2000-04-10') or (key < 5)) and ((ds > '2000-04-08') or (value = 'val_5'))) (type: boolean) - Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 15 Data size: 4170 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 -where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 -where (ds < '2000-04-10' or key < 5) and (ds > '2000-04-08' or value == 'val_5') order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-10 -0 val_0 2000-04-10 -0 val_0 2000-04-10 -2 val_2 2000-04-09 -2 val_2 2000-04-10 -4 val_4 2000-04-09 -4 val_4 2000-04-10 -5 val_5 2000-04-08 -5 val_5 2000-04-08 -5 val_5 2000-04-08 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -8 val_8 2000-04-09 -9 val_9 2000-04-09 -10 val_10 2000-04-09 -11 val_11 2000-04-09 -12 val_12 2000-04-09 -12 val_12 2000-04-09 -15 val_15 2000-04-09 -15 val_15 2000-04-09 -17 val_17 2000-04-09 -18 val_18 2000-04-09 -18 val_18 2000-04-09 -19 val_19 2000-04-09 -PREHOOK: query: explain extended select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT CAST(14 AS INTEGER) AS `key`, `value` -FROM (SELECT `value` -FROM `default`.`pcr_t1` -WHERE `key` = 14 AND `ds` IN ('2000-04-08', '2000-04-09') -ORDER BY `value`) AS `t1` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: ((key = 14) and (ds) IN ('2000-04-08', '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key = 14) (type: boolean) - Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 3 Data size: 270 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [$hdt$_0:pcr_t1] - /pcr_t1/ds=2000-04-09 [$hdt$_0:pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: 14 (type: int), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value from pcr_t1 where (ds='2000-04-08' or ds='2000-04-09') and key=14 order by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -PREHOOK: query: explain extended select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value` -FROM `default`.`pcr_t1` -WHERE `ds` IN ('2000-04-08', '2000-04-09') -ORDER BY `key`, `value` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 3760 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value from pcr_t1 where ds='2000-04-08' or ds='2000-04-09' order by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -2 val_2 -2 val_2 -4 val_4 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -8 val_8 -9 val_9 -9 val_9 -10 val_10 -10 val_10 -11 val_11 -11 val_11 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -17 val_17 -17 val_17 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -19 val_19 -19 val_19 -PREHOOK: query: explain extended select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value` -FROM `default`.`pcr_t1` -WHERE `ds` >= '2000-04-08' OR `ds` < '2000-04-10' -ORDER BY `key`, `value` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: ((ds >= '2000-04-08') or (ds < '2000-04-10')) (type: boolean) - Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select key, value from pcr_t1 where ds>='2000-04-08' or ds<'2000-04-10' order by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -2 val_2 -2 val_2 -2 val_2 -4 val_4 -4 val_4 -4 val_4 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -5 val_5 -8 val_8 -8 val_8 -8 val_8 -9 val_9 -9 val_9 -9 val_9 -10 val_10 -10 val_10 -10 val_10 -11 val_11 -11 val_11 -11 val_11 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -12 val_12 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -15 val_15 -17 val_17 -17 val_17 -17 val_17 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -18 val_18 -19 val_19 -19 val_19 -19 val_19 -PREHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE ROW(`key`, `ds`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) -ORDER BY `key`, `value`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -2 val_2 2000-04-09 -PREHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` -FROM (SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`pcr_t1` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`pcr_t1` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -#### A masked pattern was here #### -POSTHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -#### A masked pattern was here #### -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -2 val_2 2000-04-08 2 val_2 2000-04-08 -4 val_4 2000-04-08 4 val_4 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -8 val_8 2000-04-08 8 val_8 2000-04-08 -9 val_9 2000-04-08 9 val_9 2000-04-08 -10 val_10 2000-04-08 10 val_10 2000-04-08 -11 val_11 2000-04-08 11 val_11 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -17 val_17 2000-04-08 17 val_17 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -19 val_19 2000-04-08 19 val_19 2000-04-08 -PREHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` -FROM (SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`pcr_t1` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`pcr_t1` -WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1] - /pcr_t1/ds=2000-04-09 [$hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select * from pcr_t1 t1 join pcr_t1 t2 on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -#### A masked pattern was here #### -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -0 val_0 2000-04-08 0 val_0 2000-04-09 -2 val_2 2000-04-08 2 val_2 2000-04-09 -4 val_4 2000-04-08 4 val_4 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -5 val_5 2000-04-08 5 val_5 2000-04-09 -8 val_8 2000-04-08 8 val_8 2000-04-09 -9 val_9 2000-04-08 9 val_9 2000-04-09 -10 val_10 2000-04-08 10 val_10 2000-04-09 -11 val_11 2000-04-08 11 val_11 2000-04-09 -12 val_12 2000-04-08 12 val_12 2000-04-09 -12 val_12 2000-04-08 12 val_12 2000-04-09 -12 val_12 2000-04-08 12 val_12 2000-04-09 -12 val_12 2000-04-08 12 val_12 2000-04-09 -15 val_15 2000-04-08 15 val_15 2000-04-09 -15 val_15 2000-04-08 15 val_15 2000-04-09 -15 val_15 2000-04-08 15 val_15 2000-04-09 -15 val_15 2000-04-08 15 val_15 2000-04-09 -17 val_17 2000-04-08 17 val_17 2000-04-09 -18 val_18 2000-04-08 18 val_18 2000-04-09 -18 val_18 2000-04-08 18 val_18 2000-04-09 -18 val_18 2000-04-08 18 val_18 2000-04-09 -18 val_18 2000-04-08 18 val_18 2000-04-09 -19 val_19 2000-04-08 19 val_19 2000-04-09 -PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-11') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1@ds=2000-04-11 -POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-11') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1@ds=2000-04-11 -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-11).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -PREHOOK: Input: default@pcr_t1@ds=2000-04-11 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-11 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE `ds` > '2000-04-08' AND `ds` < '2000-04-11' OR `ds` BETWEEN '2000-04-08' AND '2000-04-11' AND `key` = 2 -ORDER BY `key`, `value`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) - Statistics: Num rows: 80 Data size: 22240 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds > '2000-04-08') and (ds < '2000-04-11')) or (key = 2)) (type: boolean) - Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] - /pcr_t1/ds=2000-04-11 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 14 Data size: 3892 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -PREHOOK: Input: default@pcr_t1@ds=2000-04-11 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds>='2000-04-08' and ds<='2000-04-11' and key=2) order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-11 -#### A masked pattern was here #### -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-10 -0 val_0 2000-04-10 -0 val_0 2000-04-10 -2 val_2 2000-04-08 -2 val_2 2000-04-09 -2 val_2 2000-04-10 -2 val_2 2000-04-11 -4 val_4 2000-04-09 -4 val_4 2000-04-10 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -8 val_8 2000-04-09 -8 val_8 2000-04-10 -9 val_9 2000-04-09 -9 val_9 2000-04-10 -10 val_10 2000-04-09 -10 val_10 2000-04-10 -11 val_11 2000-04-09 -11 val_11 2000-04-10 -12 val_12 2000-04-09 -12 val_12 2000-04-09 -12 val_12 2000-04-10 -12 val_12 2000-04-10 -15 val_15 2000-04-09 -15 val_15 2000-04-09 -15 val_15 2000-04-10 -15 val_15 2000-04-10 -17 val_17 2000-04-09 -17 val_17 2000-04-10 -18 val_18 2000-04-09 -18 val_18 2000-04-09 -18 val_18 2000-04-10 -18 val_18 2000-04-10 -19 val_19 2000-04-09 -19 val_19 2000-04-10 -PREHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1` -WHERE `ds` > '2000-04-08' AND `ds` < '2000-04-11' OR `ds` <= '2000-04-09' AND `key` = 2 -ORDER BY `key`, `value`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - filterExpr: ((ds > '2000-04-08') or ((ds <= '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((ds > '2000-04-08') or ((ds <= '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - /pcr_t1/ds=2000-04-09 [pcr_t1] - /pcr_t1/ds=2000-04-10 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 22 Data size: 6116 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_t1 where (ds>'2000-04-08' and ds<'2000-04-11') or (ds<='2000-04-09' and key=2) order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-10 -#### A masked pattern was here #### -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-10 -0 val_0 2000-04-10 -0 val_0 2000-04-10 -2 val_2 2000-04-08 -2 val_2 2000-04-09 -2 val_2 2000-04-10 -4 val_4 2000-04-09 -4 val_4 2000-04-10 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -5 val_5 2000-04-10 -8 val_8 2000-04-09 -8 val_8 2000-04-10 -9 val_9 2000-04-09 -9 val_9 2000-04-10 -10 val_10 2000-04-09 -10 val_10 2000-04-10 -11 val_11 2000-04-09 -11 val_11 2000-04-10 -12 val_12 2000-04-09 -12 val_12 2000-04-09 -12 val_12 2000-04-10 -12 val_12 2000-04-10 -15 val_15 2000-04-09 -15 val_15 2000-04-09 -15 val_15 2000-04-10 -15 val_15 2000-04-10 -17 val_17 2000-04-09 -17 val_17 2000-04-10 -18 val_18 2000-04-09 -18 val_18 2000-04-09 -18 val_18 2000-04-10 -18 val_18 2000-04-10 -19 val_19 2000-04-09 -19 val_19 2000-04-10 -PREHOOK: query: create table pcr_t2 (key int, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_t2 -POSTHOOK: query: create table pcr_t2 (key int, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_t2 -PREHOOK: query: create table pcr_t3 (key int, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_t3 -POSTHOOK: query: create table pcr_t3 (key int, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_t3 -PREHOOK: query: explain extended -from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Output: default@pcr_t2 -PREHOOK: Output: default@pcr_t3 -POSTHOOK: query: explain extended -from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Output: default@pcr_t2 -POSTHOOK: Output: default@pcr_t3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0, Stage-10 - Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-9 depends on stages: Stage-1, Stage-10 - Stage-10 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 2 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t3 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t3 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t3 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types struct,struct - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-8 - Conditional Operator - - Stage: Stage-5 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - - Stage: Stage-3 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.pcr_t2 - Is Table Level Stats: true - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10004 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - name: default.pcr_t2 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10004 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - name: default.pcr_t2 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-7 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-1 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t3 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct pcr_t3 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t3 - - Stage: Stage-9 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.pcr_t3 - Is Table Level Stats: true - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10005 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types struct,struct - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types struct,struct - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - -PREHOOK: query: from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Output: default@pcr_t2 -PREHOOK: Output: default@pcr_t3 -POSTHOOK: query: from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Output: default@pcr_t2 -POSTHOOK: Output: default@pcr_t3 -POSTHOOK: Lineage: pcr_t2.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: pcr_t2.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: pcr_t3.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: pcr_t3.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: explain extended -from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Output: default@pcr_t2 -PREHOOK: Output: default@pcr_t3 -POSTHOOK: query: explain extended -from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Output: default@pcr_t2 -POSTHOOK: Output: default@pcr_t3 -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 - Stage-5 - Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 - Stage-3 depends on stages: Stage-0, Stage-10 - Stage-4 - Stage-6 - Stage-7 depends on stages: Stage-6 - Stage-1 depends on stages: Stage-2 - Stage-9 depends on stages: Stage-1, Stage-10 - Stage-10 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key = 2) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 2 (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: 2 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Filter Operator - isSamplingPred: false - predicate: (key = 3) (type: boolean) - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 3 (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 2 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t3 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t3 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t3 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: 3 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types struct,struct - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1 - name: default.pcr_t1 - Truncated Path -> Alias: - /pcr_t1/ds=2000-04-08 [pcr_t1] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-8 - Conditional Operator - - Stage: Stage-5 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - - Stage: Stage-3 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.pcr_t2 - Is Table Level Stats: true - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10004 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - name: default.pcr_t2 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10004 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t2 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2 - name: default.pcr_t2 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-7 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-1 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t3 - numFiles 1 - numRows 20 - rawDataSize 160 - serialization.ddl struct pcr_t3 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t3 - - Stage: Stage-9 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.pcr_t3 - Is Table Level Stats: true - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10005 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types struct,struct - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1 - columns.types struct,struct - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - -PREHOOK: query: from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1 -PREHOOK: Input: default@pcr_t1@ds=2000-04-08 -PREHOOK: Output: default@pcr_t2 -PREHOOK: Output: default@pcr_t3 -POSTHOOK: query: from pcr_t1 -insert overwrite table pcr_t2 select key, value where ds='2000-04-08' and key=2 -insert overwrite table pcr_t3 select key, value where ds='2000-04-08' and key=3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 -POSTHOOK: Output: default@pcr_t2 -POSTHOOK: Output: default@pcr_t3 -POSTHOOK: Lineage: pcr_t2.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: pcr_t2.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: pcr_t3.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: pcr_t3.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: explain extended select key, value from srcpart where ds='2008-04-08' and hr=11 order by key limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value from srcpart where ds='2008-04-08' and hr=11 order by key limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value` -FROM `default`.`srcpart` -WHERE `ds` = '2008-04-08' AND `hr` = 11 -ORDER BY `key` -LIMIT 10 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - TopN: 10 - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: select key, value from srcpart where ds='2008-04-04' and hr=11 order by key limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -#### A masked pattern was here #### -POSTHOOK: query: select key, value from srcpart where ds='2008-04-04' and hr=11 order by key limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -#### A masked pattern was here #### -PREHOOK: query: explain extended select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` -FROM (SELECT `key`, `value`, `hr` -FROM `default`.`srcpart` -WHERE `key` = 11 AND `hr` IN ('11', '12') AND `ds` = '2008-04-08' -ORDER BY `key`, `hr`) AS `t1` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: ((UDFToDouble(key) = 11.0D) and (hr) IN ('11', '12') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (UDFToDouble(key) = 11.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 228000 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds, hr from srcpart where ds='2008-04-08' and (hr='11' or hr='12') and key=11 order by key, ds, hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -11 val_11 2008-04-08 11 -11 val_11 2008-04-08 12 -PREHOOK: query: explain extended select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds`, CAST('11' AS STRING) AS `hr` -FROM (SELECT `key`, `value`, `ds` -FROM `default`.`srcpart` -WHERE `key` = 11 AND `hr` = '11' -ORDER BY `key`, `ds`) AS `t1` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: ((UDFToDouble(key) = 11.0D) and (hr = '11')) (type: boolean) - Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (UDFToDouble(key) = 11.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 500 Data size: 181000 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:srcpart] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 224000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 224000 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds, hr from srcpart where hr='11' and key=11 order by key, ds, hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -11 val_11 2008-04-08 11 -11 val_11 2008-04-09 11 -PREHOOK: query: drop table pcr_t1 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_t1 -PREHOOK: Output: default@pcr_t1 -POSTHOOK: query: drop table pcr_t1 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_t1 -POSTHOOK: Output: default@pcr_t1 -PREHOOK: query: drop table pcr_t2 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_t2 -PREHOOK: Output: default@pcr_t2 -POSTHOOK: query: drop table pcr_t2 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_t2 -POSTHOOK: Output: default@pcr_t2 -PREHOOK: query: drop table pcr_t3 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_t3 -PREHOOK: Output: default@pcr_t3 -POSTHOOK: query: drop table pcr_t3 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_t3 -POSTHOOK: Output: default@pcr_t3 -PREHOOK: query: drop table pcr_foo -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_foo -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table pcr_foo (key int, value string) partitioned by (ds int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_foo -POSTHOOK: query: create table pcr_foo (key int, value string) partitioned by (ds int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_foo -PREHOOK: query: insert overwrite table pcr_foo partition (ds=3) select * from src where key < 10 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_foo@ds=3 -POSTHOOK: query: insert overwrite table pcr_foo partition (ds=3) select * from src where key < 10 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_foo@ds=3 -POSTHOOK: Lineage: pcr_foo PARTITION(ds=3).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_foo PARTITION(ds=3).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_foo partition (ds=5) select * from src where key < 10 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_foo@ds=5 -POSTHOOK: query: insert overwrite table pcr_foo partition (ds=5) select * from src where key < 10 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_foo@ds=5 -POSTHOOK: Lineage: pcr_foo PARTITION(ds=5).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_foo PARTITION(ds=5).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_foo partition (ds=7) select * from src where key < 10 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_foo@ds=7 -POSTHOOK: query: insert overwrite table pcr_foo partition (ds=7) select * from src where key < 10 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_foo@ds=7 -POSTHOOK: Lineage: pcr_foo PARTITION(ds=7).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_foo PARTITION(ds=7).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select key, value, ds from pcr_foo where (ds % 2 == 1) -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_foo -PREHOOK: Input: default@pcr_foo@ds=3 -PREHOOK: Input: default@pcr_foo@ds=5 -PREHOOK: Input: default@pcr_foo@ds=7 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_foo where (ds % 2 == 1) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_foo -POSTHOOK: Input: default@pcr_foo@ds=3 -POSTHOOK: Input: default@pcr_foo@ds=5 -POSTHOOK: Input: default@pcr_foo@ds=7 -#### A masked pattern was here #### -0 val_0 3 -0 val_0 3 -0 val_0 3 -2 val_2 3 -4 val_4 3 -5 val_5 3 -5 val_5 3 -5 val_5 3 -8 val_8 3 -9 val_9 3 -0 val_0 5 -0 val_0 5 -0 val_0 5 -2 val_2 5 -4 val_4 5 -5 val_5 5 -5 val_5 5 -5 val_5 5 -8 val_8 5 -9 val_9 5 -0 val_0 7 -0 val_0 7 -0 val_0 7 -2 val_2 7 -4 val_4 7 -5 val_5 7 -5 val_5 7 -5 val_5 7 -8 val_8 7 -9 val_9 7 -PREHOOK: query: select key, value, ds from pcr_foo where (ds / 3 < 2) -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_foo -PREHOOK: Input: default@pcr_foo@ds=3 -PREHOOK: Input: default@pcr_foo@ds=5 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from pcr_foo where (ds / 3 < 2) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_foo -POSTHOOK: Input: default@pcr_foo@ds=3 -POSTHOOK: Input: default@pcr_foo@ds=5 -#### A masked pattern was here #### -0 val_0 3 -0 val_0 3 -0 val_0 3 -2 val_2 3 -4 val_4 3 -5 val_5 3 -5 val_5 3 -5 val_5 3 -8 val_8 3 -9 val_9 3 -0 val_0 5 -0 val_0 5 -0 val_0 5 -2 val_2 5 -4 val_4 5 -5 val_5 5 -5 val_5 5 -5 val_5 5 -8 val_8 5 -9 val_9 5 -PREHOOK: query: drop table pcr_foo -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_foo -PREHOOK: Output: default@pcr_foo -POSTHOOK: query: drop table pcr_foo -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_foo -POSTHOOK: Output: default@pcr_foo -PREHOOK: query: create table ab(strct struct) -row format delimited - fields terminated by '\t' - collection items terminated by '\001' -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@ab -POSTHOOK: query: create table ab(strct struct) -row format delimited - fields terminated by '\t' - collection items terminated by '\001' -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@ab -PREHOOK: query: load data local inpath '../../data/files/kv1.txt' -overwrite into table ab -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@ab -POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' -overwrite into table ab -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@ab -PREHOOK: query: drop table foo_field -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table foo_field -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table foo_field (s struct) partitioned by (ds int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@foo_field -POSTHOOK: query: create table foo_field (s struct) partitioned by (ds int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@foo_field -PREHOOK: query: insert overwrite table foo_field partition (ds=5) select strct from ab where strct.a < 10 limit 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@ab -PREHOOK: Output: default@foo_field@ds=5 -POSTHOOK: query: insert overwrite table foo_field partition (ds=5) select strct from ab where strct.a < 10 limit 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ab -POSTHOOK: Output: default@foo_field@ds=5 -POSTHOOK: Lineage: foo_field PARTITION(ds=5).s SIMPLE [(ab)ab.FieldSchema(name:strct, type:struct, comment:null), ] -PREHOOK: query: insert overwrite table foo_field partition (ds=7) select strct from ab where strct.a > 190 limit 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@ab -PREHOOK: Output: default@foo_field@ds=7 -POSTHOOK: query: insert overwrite table foo_field partition (ds=7) select strct from ab where strct.a > 190 limit 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ab -POSTHOOK: Output: default@foo_field@ds=7 -POSTHOOK: Lineage: foo_field PARTITION(ds=7).s SIMPLE [(ab)ab.FieldSchema(name:strct, type:struct, comment:null), ] -PREHOOK: query: select s,ds from foo_field where ((ds + s.a) > 0) order by ds,s -PREHOOK: type: QUERY -PREHOOK: Input: default@foo_field -PREHOOK: Input: default@foo_field@ds=5 -PREHOOK: Input: default@foo_field@ds=7 -#### A masked pattern was here #### -POSTHOOK: query: select s,ds from foo_field where ((ds + s.a) > 0) order by ds,s -POSTHOOK: type: QUERY -POSTHOOK: Input: default@foo_field -POSTHOOK: Input: default@foo_field@ds=5 -POSTHOOK: Input: default@foo_field@ds=7 -#### A masked pattern was here #### -{"a":0,"b":"val_0"} 5 -{"a":4,"b":"val_4"} 5 -{"a":238,"b":"val_238"} 7 -{"a":311,"b":"val_311"} 7 -PREHOOK: query: drop table foo_field -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@foo_field -PREHOOK: Output: default@foo_field -POSTHOOK: query: drop table foo_field -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@foo_field -POSTHOOK: Output: default@foo_field -PREHOOK: query: explain select key,value from srcpart where cast(hr as double) = cast(11 as double) -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: explain select key,value from srcpart where cast(hr as double) = cast(11 as double) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: explain select key,value from srcpart where hr = cast(11 as double) -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: explain select key,value from srcpart where hr = cast(11 as double) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: explain select key,value from srcpart where cast(hr as double) = 11 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: explain select key,value from srcpart where cast(hr as double) = 11 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - filterExpr: (11.0D = 11.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - diff --git ql/src/test/results/clientpositive/pointlookup2.q.out ql/src/test/results/clientpositive/pointlookup2.q.out deleted file mode 100644 index b893ecfaf9..0000000000 --- ql/src/test/results/clientpositive/pointlookup2.q.out +++ /dev/null @@ -1,3424 +0,0 @@ -PREHOOK: query: drop table pcr_t1_n2 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t1_n2 -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table pcr_t2_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t2_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table pcr_t3 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t3 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table pcr_t1_n2 (key int, value string) partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_t1_n2 -POSTHOOK: query: create table pcr_t1_n2 (key int, value string) partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_t1_n2 -PREHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-08') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-08') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-09') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-09') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-10') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n2@ds=2000-04-10 -POSTHOOK: query: insert overwrite table pcr_t1_n2 partition (ds='2000-04-10') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n2@ds=2000-04-10 -POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n2 PARTITION(ds=2000-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: create table pcr_t2_n0 (ds string, key int, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_t2_n0 -POSTHOOK: query: create table pcr_t2_n0 (ds string, key int, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_t2_n0 -PREHOOK: query: from pcr_t1_n2 -insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Output: default@pcr_t2_n0 -POSTHOOK: query: from pcr_t1_n2 -insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Output: default@pcr_t2_n0 -POSTHOOK: Lineage: pcr_t2_n0.ds SIMPLE [] -POSTHOOK: Lineage: pcr_t2_n0.key SIMPLE [(pcr_t1_n2)pcr_t1_n2.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: pcr_t2_n0.value SIMPLE [(pcr_t1_n2)pcr_t1_n2.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: from pcr_t1_n2 -insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' and key=2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Output: default@pcr_t2_n0 -POSTHOOK: query: from pcr_t1_n2 -insert overwrite table pcr_t2_n0 select ds, key, value where ds='2000-04-08' and key=2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Output: default@pcr_t2_n0 -POSTHOOK: Lineage: pcr_t2_n0.ds SIMPLE [] -POSTHOOK: Lineage: pcr_t2_n0.key SIMPLE [] -POSTHOOK: Lineage: pcr_t2_n0.value SIMPLE [(pcr_t1_n2)pcr_t1_n2.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: explain extended -select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' AND `key` = 1 OR `ds` = '2000-04-09' AND `key` = 2 -ORDER BY `key`, `value`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n2 - filterExpr: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [pcr_t1_n2] - /pcr_t1_n2/ds=2000-04-09 [pcr_t1_n2] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 1668 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` -FROM (SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' -order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' -order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` -FROM (SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-09 [$hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t0`.`ds`, `t2`.`ds` AS `ds1`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, `ds`, `ds` = '2000-04-08' AS `=`, `ds` = '2000-04-09' AS `=7` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' OR `ds` = '2000-04-09') AS `t0` -INNER JOIN (SELECT `ds`, `key`, `value`, `key` = 1 AS `=`, `key` = 2 AS `=7` -FROM `default`.`pcr_t2_n0` -WHERE `key` = 1 OR `key` = 2) AS `t2` ON `t0`.`=` AND `t2`.`=` OR `t0`.`=7` AND `t2`.`=7` -ORDER BY `t2`.`key`, `t2`.`value`, `t0`.`ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), value (type: string), ds (type: string), (ds = '2000-04-08') (type: boolean), (ds = '2000-04-09') (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 40 Data size: 11440 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 40 Data size: 11440 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string), key (type: int), value (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: pcr_t2_n0 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2_n0 - name: default.pcr_t2_n0 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-09 [$hdt$_0:t1] - /pcr_t2_n0 [$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 40 Data size: 19240 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((_col3 and _col8) or (_col4 and _col9)) (type: boolean) - Statistics: Num rows: 20 Data size: 9620 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 9300 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:string:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t0`.`ds`, `t2`.`ds` AS `ds1`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, `ds`, `key` = 1 AS `=`, `key` = 2 AS `=7` -FROM `default`.`pcr_t1_n2` -WHERE `key` = 1 OR `key` = 2) AS `t0` -INNER JOIN (SELECT `ds`, `key`, `value`, `ds` = '2000-04-08' AS `=`, `ds` = '2000-04-09' AS `=7` -FROM `default`.`pcr_t2_n0` -WHERE `ds` = '2000-04-08' OR `ds` = '2000-04-09') AS `t2` ON `t2`.`=` AND `t0`.`=` OR `t2`.`=7` AND `t0`.`=7` -ORDER BY `t0`.`key`, `t0`.`value`, `t2`.`ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 2860 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 10 Data size: 2860 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((ds = '2000-04-08') or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string), key (type: int), value (type: string), (ds = '2000-04-08') (type: boolean), (ds = '2000-04-09') (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 195 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: boolean), _col4 (type: boolean) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: pcr_t2_n0 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2_n0 - name: default.pcr_t2_n0 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-09 [$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-10 [$hdt$_0:t1] - /pcr_t2_n0 [$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 10 Data size: 4810 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((_col8 and _col3) or (_col9 and _col4)) (type: boolean) - Statistics: Num rows: 4 Data size: 1924 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 4 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:string:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -2 val_2 2000-04-09 -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -2 val_2 2000-04-08 2 val_2 2000-04-08 -4 val_4 2000-04-08 4 val_4 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -8 val_8 2000-04-08 8 val_8 2000-04-08 -9 val_9 2000-04-08 9 val_9 2000-04-08 -10 val_10 2000-04-08 10 val_10 2000-04-08 -11 val_11 2000-04-08 11 val_11 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -17 val_17 2000-04-08 17 val_17 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -19 val_19 2000-04-08 19 val_19 2000-04-08 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -10 val_10 2000-04-09 2000-04-08 2 val_2 -11 val_11 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -17 val_17 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -19 val_19 2000-04-09 2000-04-08 2 val_2 -2 val_2 2000-04-09 2000-04-08 2 val_2 -4 val_4 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -8 val_8 2000-04-09 2000-04-08 2 val_2 -9 val_9 2000-04-09 2000-04-08 2 val_2 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -10 val_10 2000-04-09 2000-04-08 2 val_2 -11 val_11 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -17 val_17 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -19 val_19 2000-04-09 2000-04-08 2 val_2 -2 val_2 2000-04-09 2000-04-08 2 val_2 -4 val_4 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -8 val_8 2000-04-09 2000-04-08 2 val_2 -9 val_9 2000-04-09 2000-04-08 2 val_2 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -PREHOOK: query: explain extended -select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`pcr_t1_n2` -WHERE ROW(`key`, `ds`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) -ORDER BY `key`, `value`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n2 - filterExpr: ((struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [pcr_t1_n2] - /pcr_t1_n2/ds=2000-04-09 [pcr_t1_n2] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` -FROM (SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' -order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09' -order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` -FROM (SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`pcr_t1_n2` -WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 1880 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-09 [$hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Statistics: Num rows: 30 Data size: 5640 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 11280 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string), key (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: pcr_t2_n0 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2_n0 - name: default.pcr_t2_n0 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-09 [$hdt$_0:t1] - /pcr_t2_n0 [$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: (struct(_col2,_col4)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 18600 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:string:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 60 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 9 Data size: 2502 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string), key (type: int), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 187 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n2 - partition_columns ds - partition_columns.types string - serialization.ddl struct pcr_t1_n2 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n2 - name: default.pcr_t1_n2 -#### A masked pattern was here #### - Partition - base file name: pcr_t2_n0 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns ds,key,value - columns.comments - columns.types string:int:string -#### A masked pattern was here #### - name default.pcr_t2_n0 - numFiles 1 - numRows 1 - rawDataSize 18 - serialization.ddl struct pcr_t2_n0 { string ds, i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 19 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t2_n0 - name: default.pcr_t2_n0 - Truncated Path -> Alias: - /pcr_t1_n2/ds=2000-04-08 [$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-09 [$hdt$_0:t1] - /pcr_t1_n2/ds=2000-04-10 [$hdt$_0:t1] - /pcr_t2_n0 [$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: (struct(_col0,_col3)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 9 Data size: 4185 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int:string:string:string:int:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds -from pcr_t1_n2 -where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2) -order by key, value, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -#### A masked pattern was here #### -2 val_2 2000-04-09 -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t1_n2 t2 -on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08' -order by t1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -#### A masked pattern was here #### -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -0 val_0 2000-04-08 0 val_0 2000-04-08 -2 val_2 2000-04-08 2 val_2 2000-04-08 -4 val_4 2000-04-08 4 val_4 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -5 val_5 2000-04-08 5 val_5 2000-04-08 -8 val_8 2000-04-08 8 val_8 2000-04-08 -9 val_9 2000-04-08 9 val_9 2000-04-08 -10 val_10 2000-04-08 10 val_10 2000-04-08 -11 val_11 2000-04-08 11 val_11 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -12 val_12 2000-04-08 12 val_12 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -15 val_15 2000-04-08 15 val_15 2000-04-08 -17 val_17 2000-04-08 17 val_17 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -18 val_18 2000-04-08 18 val_18 2000-04-08 -19 val_19 2000-04-08 19 val_19 2000-04-08 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -10 val_10 2000-04-09 2000-04-08 2 val_2 -11 val_11 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -17 val_17 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -19 val_19 2000-04-09 2000-04-08 2 val_2 -2 val_2 2000-04-09 2000-04-08 2 val_2 -4 val_4 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -8 val_8 2000-04-09 2000-04-08 2 val_2 -9 val_9 2000-04-09 2000-04-08 2 val_2 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -0 val_0 2000-04-09 2000-04-08 2 val_2 -10 val_10 2000-04-09 2000-04-08 2 val_2 -11 val_11 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -12 val_12 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -15 val_15 2000-04-09 2000-04-08 2 val_2 -17 val_17 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -18 val_18 2000-04-09 2000-04-08 2 val_2 -19 val_19 2000-04-09 2000-04-08 2 val_2 -2 val_2 2000-04-09 2000-04-08 2 val_2 -4 val_4 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -5 val_5 2000-04-09 2000-04-08 2 val_2 -8 val_8 2000-04-09 2000-04-08 2 val_2 -9 val_9 2000-04-09 2000-04-08 2 val_2 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -PREHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -PREHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n2 t1 join pcr_t2_n0 t2 -where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2) -order by t1.key, t1.value, t2.ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-08 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-09 -POSTHOOK: Input: default@pcr_t1_n2@ds=2000-04-10 -POSTHOOK: Input: default@pcr_t2_n0 -#### A masked pattern was here #### -PREHOOK: query: drop table pcr_t1_n2 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_t1_n2 -PREHOOK: Output: default@pcr_t1_n2 -POSTHOOK: query: drop table pcr_t1_n2 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_t1_n2 -POSTHOOK: Output: default@pcr_t1_n2 -PREHOOK: query: drop table pcr_t2_n0 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_t2_n0 -PREHOOK: Output: default@pcr_t2_n0 -POSTHOOK: query: drop table pcr_t2_n0 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_t2_n0 -POSTHOOK: Output: default@pcr_t2_n0 -PREHOOK: query: drop table pcr_t3 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t3 -POSTHOOK: type: DROPTABLE diff --git ql/src/test/results/clientpositive/pointlookup3.q.out ql/src/test/results/clientpositive/pointlookup3.q.out deleted file mode 100644 index 6b3a50d680..0000000000 --- ql/src/test/results/clientpositive/pointlookup3.q.out +++ /dev/null @@ -1,2972 +0,0 @@ -PREHOOK: query: drop table pcr_t1_n1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t1_n1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table pcr_t1_n1 (key int, value string) partitioned by (ds1 string, ds2 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_t1_n1 -POSTHOOK: query: create table pcr_t1_n1 (key int, value string) partitioned by (ds1 string, ds2 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_t1_n1 -PREHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-08,ds2=2001-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-08,ds2=2001-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-09,ds2=2001-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-09,ds2=2001-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -POSTHOOK: query: insert overwrite table pcr_t1_n1 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-10,ds2=2001-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n1 PARTITION(ds1=2000-04-10,ds2=2001-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-08' AND `key` = 1 OR `ds1` = '2000-04-09' AND `key` = 2 -ORDER BY `key`, `value`, `ds1`, `ds2` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n1 - filterExpr: (((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n1] - /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, CAST('2001-04-08' AS STRING) AS `ds2` -FROM (SELECT `key`, `value`, `ds1` -FROM `default`.`pcr_t1_n1` -WHERE (`ds1` = '2000-04-08' AND `key` = 1 OR `ds1` = '2000-04-09' AND `key` = 2) AND `ds2` = '2001-04-08' -ORDER BY `key`, `value`, `ds1`) AS `t1` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n1 - filterExpr: ((((ds1 = '2000-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (key = 2))) and (ds2 = '2001-04-08')) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key = 1) (type: boolean) - Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 2 Data size: 556 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:pcr_t1_n1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, `t3`.`ds1` AS `ds11`, CAST('2001-04-08' AS STRING) AS `ds21` -FROM (SELECT * -FROM (SELECT `key`, `value`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, `ds1` -FROM `default`.`pcr_t1_n1` -WHERE `ds2` = '2001-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds2 = '2001-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col3 (type: int), _col4 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), '2001-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int:string:string:string:int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds11`, `t3`.`ds20` AS `ds21` -FROM (SELECT * -FROM (SELECT `key`, `value`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds1 = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:$hdt$_0:t1] - /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col3 (type: int), _col4 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2000-04-09' (type: string), VALUE._col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int:string:string:string:int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t0`.`ds1`, `t0`.`ds2`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1`, `t2`.`ds1` AS `ds11`, `t2`.`ds2` AS `ds21` -FROM (SELECT `key`, `value`, `ds1`, `ds2`, `ds1` = '2000-04-08' AS `=`, `ds1` = '2000-04-09' AS `=8` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-08' OR `ds1` = '2000-04-09') AS `t0` -INNER JOIN (SELECT `key`, `value`, `ds1`, `ds2`, `key` = 1 AS `=`, `key` = 2 AS `=8` -FROM `default`.`pcr_t1_n1` -WHERE `key` = 1 OR `key` = 2) AS `t2` ON `t0`.`=` AND `t2`.`=` OR `t0`.`=8` AND `t2`.`=8` -ORDER BY `t2`.`key`, `t2`.`value`, `t0`.`ds1` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds1 = '2000-04-08') or (ds1 = '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string), (ds1 = '2000-04-08') (type: boolean), (ds1 = '2000-04-09') (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 40 Data size: 18800 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 40 Data size: 18800 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: boolean), _col5 (type: boolean) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 60 Data size: 27720 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key = 1) or (key = 2)) (type: boolean) - Statistics: Num rows: 10 Data size: 4620 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string), (key = 1) (type: boolean), (key = 2) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 10 Data size: 4700 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 10 Data size: 4700 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: boolean), _col5 (type: boolean) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-10 - ds2 2001-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:t1, $hdt$_1:t2] - /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_0:t1, $hdt$_1:t2] - /pcr_t1_n1/ds1=2000-04-10/ds2=2001-04-10 [$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 400 Data size: 376000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((_col4 and _col10) or (_col5 and _col11)) (type: boolean) - Statistics: Num rows: 200 Data size: 188000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string), _col9 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 200 Data size: 184800 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int:string:string:string:int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -2 val_2 2000-04-09 2001-04-09 -PREHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -PREHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-08 2001-04-08 -4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-08 2001-04-08 -9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-08 2001-04-08 -10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-08 2001-04-08 -11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-08 2001-04-08 -PREHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-09 2001-04-09 -4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-09 2001-04-09 -9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-09 2001-04-09 -10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-09 2001-04-09 -11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-09 2001-04-09 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -PREHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE ROW(`key`, `ds1`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) -ORDER BY `key`, `value`, `ds1`, `ds2` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n1 - filterExpr: ((struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (struct(ds1)) IN (struct('2000-04-08'), struct('2000-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n1] - /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, CAST('2001-04-08' AS STRING) AS `ds2` -FROM (SELECT `key`, `value`, `ds1` -FROM `default`.`pcr_t1_n1` -WHERE ROW(`key`, `ds1`) IN (ROW(1, '2000-04-08'), ROW(2, '2000-04-09')) AND `ds2` = '2001-04-08' -ORDER BY `key`, `value`, `ds1`) AS `t1` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n1 - filterExpr: ((struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) and (ds2 = '2001-04-08')) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(key,ds1)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean) - Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 10 Data size: 2780 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:pcr_t1_n1] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 10 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 10 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, `t3`.`ds1` AS `ds11`, CAST('2001-04-08' AS STRING) AS `ds21` -FROM (SELECT * -FROM (SELECT `key`, `value`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, `ds1` -FROM `default`.`pcr_t1_n1` -WHERE `ds2` = '2001-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds2 = '2001-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:$hdt$_0:t1, $hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col3 (type: int), _col4 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), '2001-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int:string:string:string:int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds1`, `t3`.`ds2`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds11`, `t3`.`ds20` AS `ds21` -FROM (SELECT * -FROM (SELECT `key`, `value`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, `ds2` -FROM `default`.`pcr_t1_n1` -WHERE `ds1` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t2`.`key`, `t2`.`value`) AS `t3` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((ds1 = '2000-04-08') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: ((ds1 = '2000-04-09') and key is not null) (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 20 Data size: 5560 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string), _col2 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:$hdt$_0:t1] - /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_0:$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col3 (type: int), _col4 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 30 Data size: 16680 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col5 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), '2000-04-09' (type: string), VALUE._col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 22320 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int:string:string:string:int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: (ds1) IN ('2000-04-08', '2000-04-09') (type: boolean) - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) - auto parallelism: false - TableScan - alias: t2 - filterExpr: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 60 Data size: 27720 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key) IN (1, 2) (type: boolean) - Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 9 Data size: 4158 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-10 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-10 - ds2 2001-04-10 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n1 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n1 - name: default.pcr_t1_n1 - Truncated Path -> Alias: - /pcr_t1_n1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:t1, $hdt$_1:t2] - /pcr_t1_n1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_0:t1, $hdt$_1:t2] - /pcr_t1_n1/ds1=2000-04-10/ds2=2001-04-10 [$hdt$_1:t2] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 360 Data size: 332640 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: (struct(_col2,_col4)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) - Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 180 Data size: 166320 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int:string:string:string:int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -2 val_2 2000-04-09 2001-04-09 -PREHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n1 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -PREHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -#### A masked pattern was here #### -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-08 2001-04-08 -2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-08 2001-04-08 -4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-08 2001-04-08 -8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-08 2001-04-08 -9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-08 2001-04-08 -10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-08 2001-04-08 -11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-08 2001-04-08 -17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-08 2001-04-08 -19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-08 2001-04-08 -PREHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -0 val_0 2000-04-08 2001-04-08 0 val_0 2000-04-09 2001-04-09 -2 val_2 2000-04-08 2001-04-08 2 val_2 2000-04-09 2001-04-09 -4 val_4 2000-04-08 2001-04-08 4 val_4 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -5 val_5 2000-04-08 2001-04-08 5 val_5 2000-04-09 2001-04-09 -8 val_8 2000-04-08 2001-04-08 8 val_8 2000-04-09 2001-04-09 -9 val_9 2000-04-08 2001-04-08 9 val_9 2000-04-09 2001-04-09 -10 val_10 2000-04-08 2001-04-08 10 val_10 2000-04-09 2001-04-09 -11 val_11 2000-04-08 2001-04-08 11 val_11 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -12 val_12 2000-04-08 2001-04-08 12 val_12 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -15 val_15 2000-04-08 2001-04-08 15 val_15 2000-04-09 2001-04-09 -17 val_17 2000-04-08 2001-04-08 17 val_17 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -18 val_18 2000-04-08 2001-04-08 18 val_18 2000-04-09 2001-04-09 -19 val_19 2000-04-08 2001-04-08 19 val_19 2000-04-09 2001-04-09 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -PREHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -POSTHOOK: query: select * -from pcr_t1_n1 t1 join pcr_t1_n1 t2 -where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) -order by t2.key, t2.value, t1.ds1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: Input: default@pcr_t1_n1@ds1=2000-04-10/ds2=2001-04-10 -#### A masked pattern was here #### -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -0 val_0 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -10 val_10 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -11 val_11 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -12 val_12 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -15 val_15 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -17 val_17 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -18 val_18 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -19 val_19 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -2 val_2 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -4 val_4 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -5 val_5 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -8 val_8 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-10 2001-04-10 -9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-08 2001-04-08 -9 val_9 2000-04-09 2001-04-09 2 val_2 2000-04-09 2001-04-09 -PREHOOK: query: drop table pcr_t1_n1 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_t1_n1 -PREHOOK: Output: default@pcr_t1_n1 -POSTHOOK: query: drop table pcr_t1_n1 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_t1_n1 -POSTHOOK: Output: default@pcr_t1_n1 diff --git ql/src/test/results/clientpositive/pointlookup4.q.out ql/src/test/results/clientpositive/pointlookup4.q.out deleted file mode 100644 index 2967c6208e..0000000000 --- ql/src/test/results/clientpositive/pointlookup4.q.out +++ /dev/null @@ -1,480 +0,0 @@ -PREHOOK: query: drop table pcr_t1_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pcr_t1_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table pcr_t1_n0 (key int, value string) partitioned by (ds1 string, ds2 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pcr_t1_n0 -POSTHOOK: query: create table pcr_t1_n0 (key int, value string) partitioned by (ds1 string, ds2 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pcr_t1_n0 -PREHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-08,ds2=2001-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-08,ds2=2001-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-09,ds2=2001-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-09,ds2=2001-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@pcr_t1_n0@ds1=2000-04-10/ds2=2001-04-10 -POSTHOOK: query: insert overwrite table pcr_t1_n0 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@pcr_t1_n0@ds1=2000-04-10/ds2=2001-04-10 -POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-10,ds2=2001-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: pcr_t1_n0 PARTITION(ds1=2000-04-10,ds2=2001-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n0 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n0 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` -FROM `default`.`pcr_t1_n0` -WHERE `ds1` = '2000-04-08' AND `ds2` = '2001-04-08' AND `key` = 1 OR `ds1` = '2000-04-09' AND `ds2` = '2001-04-09' AND `key` = 2 -ORDER BY `key`, `value`, `ds1`, `ds2` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n0 - filterExpr: (((ds1 = '2000-04-08') and (ds2 = '2001-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (ds2 = '2001-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (((ds1 = '2000-04-08') and (ds2 = '2001-04-08') and (key = 1)) or ((ds1 = '2000-04-09') and (ds2 = '2001-04-09') and (key = 2))) (type: boolean) - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n0 - name: default.pcr_t1_n0 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n0 - name: default.pcr_t1_n0 - Truncated Path -> Alias: - /pcr_t1_n0/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n0] - /pcr_t1_n0/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n0] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 2772 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n0 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n0 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -2 val_2 2000-04-09 2001-04-09 -PREHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n0 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n0 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds1`, `ds2` -FROM `default`.`pcr_t1_n0` -WHERE ROW(`key`, `ds1`, `ds2`) IN (ROW(1, '2000-04-08', '2001-04-08'), ROW(2, '2000-04-09', '2001-04-09')) -ORDER BY `key`, `value`, `ds1`, `ds2` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: pcr_t1_n0 - filterExpr: ((struct(key,ds1,ds2)) IN (const struct(1,'2000-04-08','2001-04-08'), const struct(2,'2000-04-09','2001-04-09')) and (struct(ds1,ds2)) IN (struct('2000-04-08','2001-04-08'), struct('2000-04-09','2001-04-09'))) (type: boolean) - Statistics: Num rows: 40 Data size: 18480 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (struct(key,ds1,ds2)) IN (const struct(1,'2000-04-08','2001-04-08'), const struct(2,'2000-04-09','2001-04-09')) (type: boolean) - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - numBuckets: -1 - sort order: ++++ - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-08 - ds2 2001-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n0 - name: default.pcr_t1_n0 -#### A masked pattern was here #### - Partition - base file name: ds2=2001-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds1 2000-04-09 - ds2 2001-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - numFiles 1 - numRows 20 - partition_columns ds1/ds2 - partition_columns.types string:string - rawDataSize 160 - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.pcr_t1_n0 - partition_columns ds1/ds2 - partition_columns.types string:string - serialization.ddl struct pcr_t1_n0 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.pcr_t1_n0 - name: default.pcr_t1_n0 - Truncated Path -> Alias: - /pcr_t1_n0/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1_n0] - /pcr_t1_n0/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1_n0] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 20 Data size: 9240 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types int:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pcr_t1_n0 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -PREHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds1, ds2 -from pcr_t1_n0 -where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-09' and key=2) -order by key, value, ds1, ds2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pcr_t1_n0 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-08/ds2=2001-04-08 -POSTHOOK: Input: default@pcr_t1_n0@ds1=2000-04-09/ds2=2001-04-09 -#### A masked pattern was here #### -2 val_2 2000-04-09 2001-04-09 -PREHOOK: query: drop table pcr_t1_n0 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pcr_t1_n0 -PREHOOK: Output: default@pcr_t1_n0 -POSTHOOK: query: drop table pcr_t1_n0 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pcr_t1_n0 -POSTHOOK: Output: default@pcr_t1_n0 diff --git ql/src/test/results/clientpositive/pointlookup5.q.out ql/src/test/results/clientpositive/pointlookup5.q.out deleted file mode 100644 index d44cb901cf..0000000000 --- ql/src/test/results/clientpositive/pointlookup5.q.out +++ /dev/null @@ -1,140 +0,0 @@ -PREHOOK: query: create table t(a integer) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t -POSTHOOK: query: create table t(a integer) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t -PREHOOK: query: create table t2(b integer) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t2 -POSTHOOK: query: create table t2(b integer) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t2 -PREHOOK: query: insert into t values (1),(2),(3),(4) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t -POSTHOOK: query: insert into t values (1),(2),(3),(4) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t -POSTHOOK: Lineage: t.a SCRIPT [] -PREHOOK: query: insert into t2 values (1),(2),(3),(4) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t2 -POSTHOOK: query: insert into t2 values (1),(2),(3),(4) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t2 -POSTHOOK: Lineage: t2.b SCRIPT [] -PREHOOK: query: explain -select * from t,t2 where - a*a=b+3 - and - a in (1,2,3,4) - and - b in (1,2,3,4) - - and ( - (a in (1,2) and b in (1,2) ) or - (a in (2,3) and b in (2,3) ) - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@t -PREHOOK: Input: default@t2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from t,t2 where - a*a=b+3 - and - a in (1,2,3,4) - and - b in (1,2,3,4) - - and ( - (a in (1,2) and b in (1,2) ) or - (a in (2,3) and b in (2,3) ) - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t -POSTHOOK: Input: default@t2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t - filterExpr: (a) IN (1, 2, 3) (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (a) IN (1, 2, 3) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int), (a * a) (type: int), (a) IN (1, 2) (type: boolean), (a) IN (2, 3) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col2 (type: boolean), _col3 (type: boolean) - TableScan - alias: t2 - filterExpr: (b) IN (1, 2, 3) (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (b) IN (1, 2, 3) (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: b (type: int), (b + 3) (type: int), (b) IN (1, 2) (type: boolean), (b) IN (2, 3) (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col2 (type: boolean), _col3 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col0, _col2, _col3, _col4, _col6, _col7 - Statistics: Num rows: 3 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col2 and _col6) or (_col3 and _col7)) (type: boolean) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col4 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/position_alias_test_1.q.out ql/src/test/results/clientpositive/position_alias_test_1.q.out deleted file mode 100644 index 18861f20b9..0000000000 --- ql/src/test/results/clientpositive/position_alias_test_1.q.out +++ /dev/null @@ -1,200 +0,0 @@ -PREHOOK: query: create table alias_test_01(a INT, b STRING) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@alias_test_01 -POSTHOOK: query: create table alias_test_01(a INT, b STRING) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@alias_test_01 -PREHOOK: query: create table alias_test_02(a INT, b STRING) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@alias_test_02 -POSTHOOK: query: create table alias_test_02(a INT, b STRING) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@alias_test_02 -PREHOOK: query: create table alias_test_03(a INT, b STRING) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@alias_test_03 -POSTHOOK: query: create table alias_test_03(a INT, b STRING) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@alias_test_03 -Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain - select * from - alias_test_01 alias01 - left join - ( - select 2017 as a, b from alias_test_02 group by 1, 2 - ) alias02 - on alias01.a = alias02.a - left join - alias_test_03 alias03 - on alias01.a = alias03.a -PREHOOK: type: QUERY -PREHOOK: Input: default@alias_test_01 -PREHOOK: Input: default@alias_test_02 -PREHOOK: Input: default@alias_test_03 -#### A masked pattern was here #### -POSTHOOK: query: explain - select * from - alias_test_01 alias01 - left join - ( - select 2017 as a, b from alias_test_02 group by 1, 2 - ) alias02 - on alias01.a = alias02.a - left join - alias_test_03 alias03 - on alias01.a = alias03.a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alias_test_01 -POSTHOOK: Input: default@alias_test_02 -POSTHOOK: Input: default@alias_test_03 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-1 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: alias_test_02 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: b (type: string) - outputColumnNames: b - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: b (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 2017 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: alias01 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: a (type: int), b (type: string), (a = 2017) (type: boolean) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: boolean) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - filter predicates: - 0 {VALUE._col2} - 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 1 Data size: 373 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 373 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) - TableScan - alias: alias03 - filterExpr: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: a is not null (type: boolean) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: a (type: int), b (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: int), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 410 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/ppd2.q.out ql/src/test/results/clientpositive/ppd2.q.out deleted file mode 100644 index 986ed1c114..0000000000 --- ql/src/test/results/clientpositive/ppd2.q.out +++ /dev/null @@ -1,681 +0,0 @@ -PREHOOK: query: explain -select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: explain -select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(value) - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 > 1L) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -0 3 -100 2 -103 2 -104 2 -113 2 -118 2 -119 3 -12 2 -120 2 -125 2 -128 3 -129 2 -134 2 -137 2 -138 4 -146 2 -149 2 -15 2 -152 2 -164 2 -165 2 -167 3 -169 4 -172 2 -174 2 -175 2 -176 2 -179 2 -18 2 -187 3 -191 2 -193 3 -195 2 -197 2 -199 3 -200 2 -203 2 -205 2 -207 2 -208 3 -209 2 -213 2 -216 2 -217 2 -219 2 -221 2 -223 2 -224 2 -229 2 -230 5 -233 2 -237 2 -238 2 -239 2 -24 2 -242 2 -255 2 -256 2 -26 2 -265 2 -272 2 -273 3 -277 4 -278 2 -280 2 -281 2 -282 2 -288 2 -298 3 -307 2 -309 2 -311 3 -316 3 -317 2 -318 3 -321 2 -322 2 -325 2 -327 3 -331 2 -333 2 -342 2 -344 2 -348 5 -35 3 -353 2 -367 2 -369 3 -37 2 -382 2 -384 3 -395 2 -396 3 -397 2 -399 2 -401 5 -403 3 -404 2 -406 4 -409 3 -413 2 -414 2 -417 3 -42 2 -424 2 -429 2 -430 3 -431 3 -438 3 -439 2 -454 3 -458 2 -459 2 -462 2 -463 2 -466 3 -468 4 -469 5 -478 2 -480 3 -489 4 -492 2 -498 3 -5 3 -51 2 -58 2 -67 2 -70 3 -72 2 -76 2 -83 2 -84 2 -90 3 -95 2 -97 2 -98 2 -PREHOOK: query: EXPLAIN -SELECT user_id -FROM ( - SELECT - CAST(key AS INT) AS user_id - ,CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%') - THEN 1 - ELSE 0 END AS tag_student - FROM srcpart -) sub -WHERE sub.tag_student > 0 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT user_id -FROM ( - SELECT - CAST(key AS INT) AS user_id - ,CASE WHEN (value LIKE 'aaa%' OR value LIKE 'vvv%') - THEN 1 - ELSE 0 END AS tag_student - FROM srcpart -) sub -WHERE sub.tag_student > 0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((value like 'aaa%') or (value like 'vvv%')) (type: boolean) - Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(key) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 20) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - TableScan - alias: y - filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 20) (type: boolean) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: explain -select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(value) - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 > 1L) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -POSTHOOK: query: select b.key,b.cc -from ( - select a.* - from ( - select key, count(value) as cc - from srcpart a - where a.ds = '2008-04-08' and a.hr = '11' - group by key - )a - distribute by a.key - sort by a.key,a.cc desc) b -where b.cc>1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -#### A masked pattern was here #### -0 3 -100 2 -103 2 -104 2 -113 2 -118 2 -119 3 -12 2 -120 2 -125 2 -128 3 -129 2 -134 2 -137 2 -138 4 -146 2 -149 2 -15 2 -152 2 -164 2 -165 2 -167 3 -169 4 -172 2 -174 2 -175 2 -176 2 -179 2 -18 2 -187 3 -191 2 -193 3 -195 2 -197 2 -199 3 -200 2 -203 2 -205 2 -207 2 -208 3 -209 2 -213 2 -216 2 -217 2 -219 2 -221 2 -223 2 -224 2 -229 2 -230 5 -233 2 -237 2 -238 2 -239 2 -24 2 -242 2 -255 2 -256 2 -26 2 -265 2 -272 2 -273 3 -277 4 -278 2 -280 2 -281 2 -282 2 -288 2 -298 3 -307 2 -309 2 -311 3 -316 3 -317 2 -318 3 -321 2 -322 2 -325 2 -327 3 -331 2 -333 2 -342 2 -344 2 -348 5 -35 3 -353 2 -367 2 -369 3 -37 2 -382 2 -384 3 -395 2 -396 3 -397 2 -399 2 -401 5 -403 3 -404 2 -406 4 -409 3 -413 2 -414 2 -417 3 -42 2 -424 2 -429 2 -430 3 -431 3 -438 3 -439 2 -454 3 -458 2 -459 2 -462 2 -463 2 -466 3 -468 4 -469 5 -478 2 -480 3 -489 4 -492 2 -498 3 -5 3 -51 2 -58 2 -67 2 -70 3 -72 2 -76 2 -83 2 -84 2 -90 3 -95 2 -97 2 -98 2 diff --git ql/src/test/results/clientpositive/ppd_clusterby.q.out ql/src/test/results/clientpositive/ppd_clusterby.q.out deleted file mode 100644 index f22da17edb..0000000000 --- ql/src/test/results/clientpositive/ppd_clusterby.q.out +++ /dev/null @@ -1,345 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 10) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -10 val_10 -PREHOOK: query: EXPLAIN -SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (key = 20)) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - TableScan - alias: y - filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (key = 20)) (type: boolean) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -20 val_20 20 -PREHOOK: query: EXPLAIN -SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (key = 10) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 10) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM SRC x where x.key = 10 CLUSTER BY x.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -10 val_10 -PREHOOK: query: EXPLAIN -SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 20) (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - TableScan - alias: y - filterExpr: (key = 20) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 20) (type: boolean) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT x.key, x.value as v1, y.key FROM SRC x JOIN SRC y ON (x.key = y.key) where x.key = 20 CLUSTER BY v1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -20 val_20 20 diff --git ql/src/test/results/clientpositive/ppd_constant_expr.q.out ql/src/test/results/clientpositive/ppd_constant_expr.q.out deleted file mode 100644 index dd30a1dcca..0000000000 --- ql/src/test/results/clientpositive/ppd_constant_expr.q.out +++ /dev/null @@ -1,354 +0,0 @@ -PREHOOK: query: CREATE TABLE ppd_constant_expr(c1 STRING, c2 INT, c3 DOUBLE) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@ppd_constant_expr -POSTHOOK: query: CREATE TABLE ppd_constant_expr(c1 STRING, c2 INT, c3 DOUBLE) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@ppd_constant_expr -PREHOOK: query: EXPLAIN -FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -PREHOOK: Output: default@ppd_constant_expr -POSTHOOK: query: EXPLAIN -FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -POSTHOOK: Output: default@ppd_constant_expr -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: null (type: string), null (type: int), null (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) - outputColumnNames: c1, c2, c3 - Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: c1, c2, c3 - Column Types: string, int, double - Table: default.ppd_constant_expr - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -PREHOOK: Output: default@ppd_constant_expr -POSTHOOK: query: FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -POSTHOOK: Output: default@ppd_constant_expr -POSTHOOK: Lineage: ppd_constant_expr.c1 EXPRESSION [] -POSTHOOK: Lineage: ppd_constant_expr.c2 EXPRESSION [] -POSTHOOK: Lineage: ppd_constant_expr.c3 EXPRESSION [] -PREHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr -PREHOOK: type: QUERY -PREHOOK: Input: default@ppd_constant_expr -#### A masked pattern was here #### -POSTHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ppd_constant_expr -#### A masked pattern was here #### -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -PREHOOK: query: EXPLAIN -FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -PREHOOK: Output: default@ppd_constant_expr -POSTHOOK: query: EXPLAIN -FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -POSTHOOK: Output: default@ppd_constant_expr -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: null (type: string), null (type: int), null (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - Select Operator - expressions: _col0 (type: string), _col1 (type: int), _col2 (type: double) - outputColumnNames: c1, c2, c3 - Statistics: Num rows: 25 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: c1, c2, c3 - Column Types: string, int, double - Table: default.ppd_constant_expr - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.ppd_constant_expr - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -PREHOOK: Output: default@ppd_constant_expr -POSTHOOK: query: FROM src1 -INSERT OVERWRITE TABLE ppd_constant_expr SELECT 4 + NULL, src1.key - NULL, NULL + NULL -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -POSTHOOK: Output: default@ppd_constant_expr -POSTHOOK: Lineage: ppd_constant_expr.c1 EXPRESSION [] -POSTHOOK: Lineage: ppd_constant_expr.c2 EXPRESSION [] -POSTHOOK: Lineage: ppd_constant_expr.c3 EXPRESSION [] -PREHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr -PREHOOK: type: QUERY -PREHOOK: Input: default@ppd_constant_expr -#### A masked pattern was here #### -POSTHOOK: query: SELECT ppd_constant_expr.* FROM ppd_constant_expr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ppd_constant_expr -#### A masked pattern was here #### -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL -NULL NULL NULL diff --git ql/src/test/results/clientpositive/ppd_gby2.q.out ql/src/test/results/clientpositive/ppd_gby2.q.out deleted file mode 100644 index a79c3279ab..0000000000 --- ql/src/test/results/clientpositive/ppd_gby2.q.out +++ /dev/null @@ -1,262 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) - Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(_col0) - keys: _col1 (type: bigint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: bigint) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - keys: KEY._col0 (type: bigint) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -val_4 1 -val_399 2 -val_396 3 -val_277 4 -val_348 5 -PREHOOK: query: EXPLAIN -SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (value > 'val_200') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (value > 'val_200') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 8217 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 > 30L) or (_col0 < 'val_400')) (type: boolean) - Statistics: Num rows: 54 Data size: 5346 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(_col0) - keys: _col1 (type: bigint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: bigint) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0) - keys: KEY._col0 (type: bigint) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 27 Data size: 5184 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT max(src1.c1), src1.c2 -FROM -(SELECT src.value AS c1, count(src.key) AS c2 FROM src WHERE src.value > 'val_10' GROUP BY src.value) src1 -WHERE src1.c1 > 'val_200' AND (src1.c2 > 30 OR src1.c1 < 'val_400') -GROUP BY src1.c2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -val_4 1 -val_399 2 -val_396 3 -val_277 4 -val_348 5 diff --git ql/src/test/results/clientpositive/ppd_gby_join.q.out ql/src/test/results/clientpositive/ppd_gby_join.q.out deleted file mode 100644 index a9b7593714..0000000000 --- ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ /dev/null @@ -1,548 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 56 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -200 4 -201 1 -202 1 -203 4 -205 4 -207 4 -208 9 -209 4 -213 4 -214 1 -216 4 -217 4 -218 1 -219 4 -221 4 -222 1 -223 4 -224 4 -226 1 -228 1 -229 4 -230 25 -233 4 -235 1 -237 4 -238 4 -239 4 -24 4 -241 1 -242 4 -244 1 -247 1 -248 1 -249 1 -252 1 -255 4 -256 4 -257 1 -258 1 -26 4 -260 1 -262 1 -263 1 -265 4 -266 1 -27 1 -272 4 -273 9 -274 1 -275 1 -277 16 -278 4 -28 1 -280 4 -281 4 -282 4 -283 1 -284 1 -285 1 -286 1 -287 1 -288 4 -289 1 -291 1 -292 1 -296 1 -298 9 -30 1 -302 1 -305 1 -306 1 -307 4 -308 1 -309 4 -310 1 -311 9 -315 1 -316 9 -317 4 -318 9 -321 4 -322 4 -323 1 -325 4 -327 9 -33 1 -331 4 -332 1 -333 4 -335 1 -336 1 -338 1 -339 1 -34 1 -341 1 -342 4 -344 4 -345 1 -348 25 -35 9 -351 1 -353 4 -356 1 -360 1 -362 1 -364 1 -365 1 -366 1 -367 4 -368 1 -369 9 -37 4 -373 1 -374 1 -375 1 -377 1 -378 1 -379 1 -382 4 -384 9 -386 1 -389 1 -392 1 -393 1 -394 1 -395 4 -396 9 -397 4 -399 4 -PREHOOK: query: EXPLAIN -SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and ((value < 'val_50') or (key > '2')) and (key <> '4')) (type: boolean) - Statistics: Num rows: 36 Data size: 6408 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 36 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '20') and (key < '400') and (key <> '4')) (type: boolean) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 56 Data size: 4872 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 23 Data size: 2185 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT src1.c1, count(1) -FROM -(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1 -JOIN -(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 AND src1.c1 < '400' -WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4') -GROUP BY src1.c1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -200 4 -201 1 -202 1 -203 4 -205 4 -207 4 -208 9 -209 4 -213 4 -214 1 -216 4 -217 4 -218 1 -219 4 -221 4 -222 1 -223 4 -224 4 -226 1 -228 1 -229 4 -230 25 -233 4 -235 1 -237 4 -238 4 -239 4 -24 4 -241 1 -242 4 -244 1 -247 1 -248 1 -249 1 -252 1 -255 4 -256 4 -257 1 -258 1 -26 4 -260 1 -262 1 -263 1 -265 4 -266 1 -27 1 -272 4 -273 9 -274 1 -275 1 -277 16 -278 4 -28 1 -280 4 -281 4 -282 4 -283 1 -284 1 -285 1 -286 1 -287 1 -288 4 -289 1 -291 1 -292 1 -296 1 -298 9 -30 1 -302 1 -305 1 -306 1 -307 4 -308 1 -309 4 -310 1 -311 9 -315 1 -316 9 -317 4 -318 9 -321 4 -322 4 -323 1 -325 4 -327 9 -33 1 -331 4 -332 1 -333 4 -335 1 -336 1 -338 1 -339 1 -34 1 -341 1 -342 4 -344 4 -345 1 -348 25 -35 9 -351 1 -353 4 -356 1 -360 1 -362 1 -364 1 -365 1 -366 1 -367 4 -368 1 -369 9 -37 4 -373 1 -374 1 -375 1 -377 1 -378 1 -379 1 -382 4 -384 9 -386 1 -389 1 -392 1 -393 1 -394 1 -395 4 -396 9 -397 4 -399 4 diff --git ql/src/test/results/clientpositive/ppd_join4.q.out ql/src/test/results/clientpositive/ppd_join4.q.out deleted file mode 100644 index 5e4358864d..0000000000 --- ql/src/test/results/clientpositive/ppd_join4.q.out +++ /dev/null @@ -1,128 +0,0 @@ -PREHOOK: query: create table dual(a string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dual -POSTHOOK: query: create table dual(a string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dual -PREHOOK: query: drop table if exists test_tbl -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table if exists test_tbl -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table test_tbl (id string,name string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@test_tbl -POSTHOOK: query: create table test_tbl (id string,name string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@test_tbl -PREHOOK: query: insert into table test_tbl -select 'a','b' from dual -PREHOOK: type: QUERY -PREHOOK: Input: default@dual -PREHOOK: Output: default@test_tbl -POSTHOOK: query: insert into table test_tbl -select 'a','b' from dual -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dual -POSTHOOK: Output: default@test_tbl -POSTHOOK: Lineage: test_tbl.id SIMPLE [] -POSTHOOK: Lineage: test_tbl.name SIMPLE [] -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain -select t2.* -from -(select id,name from (select id,name from test_tbl) t1 sort by id) t2 -join test_tbl t3 on (t2.id=t3.id ) -where t2.name='c' and t3.id='a' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_tbl -#### A masked pattern was here #### -POSTHOOK: query: explain -select t2.* -from -(select id,name from (select id,name from test_tbl) t1 sort by id) t2 -join test_tbl t3 on (t2.id=t3.id ) -where t2.name='c' and t3.id='a' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_tbl -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: test_tbl - filterExpr: ((name = 'c') and (id = 'a')) (type: boolean) - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((name = 'c') and (id = 'a')) (type: boolean) - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: t3 - filterExpr: (id = 'a') (type: boolean) - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (id = 'a') (type: boolean) - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'a' (type: string), 'c' (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select t2.* -from -(select id,name from (select id,name from test_tbl) t1 sort by id) t2 -join test_tbl t3 on (t2.id=t3.id ) -where t2.name='c' and t3.id='a' -PREHOOK: type: QUERY -PREHOOK: Input: default@test_tbl -#### A masked pattern was here #### -POSTHOOK: query: select t2.* -from -(select id,name from (select id,name from test_tbl) t1 sort by id) t2 -join test_tbl t3 on (t2.id=t3.id ) -where t2.name='c' and t3.id='a' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@test_tbl -#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/ppd_join5.q.out ql/src/test/results/clientpositive/ppd_join5.q.out deleted file mode 100644 index 12e7683d4d..0000000000 --- ql/src/test/results/clientpositive/ppd_join5.q.out +++ /dev/null @@ -1,319 +0,0 @@ -PREHOOK: query: create table t1_n79 (id1 string, id2 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t1_n79 -POSTHOOK: query: create table t1_n79 (id1 string, id2 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t1_n79 -PREHOOK: query: create table t2_n48 (id string, d int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t2_n48 -POSTHOOK: query: create table t2_n48 (id string, d int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t2_n48 -PREHOOK: query: from src tablesample (1 rows) - insert into table t1_n79 select 'a','a' - insert into table t2_n48 select 'a',2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@t1_n79 -PREHOOK: Output: default@t2_n48 -POSTHOOK: query: from src tablesample (1 rows) - insert into table t1_n79 select 'a','a' - insert into table t2_n48 select 'a',2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@t1_n79 -POSTHOOK: Output: default@t2_n48 -POSTHOOK: Lineage: t1_n79.id1 SIMPLE [] -POSTHOOK: Lineage: t1_n79.id2 SIMPLE [] -POSTHOOK: Lineage: t2_n48.d SIMPLE [] -POSTHOOK: Lineage: t2_n48.id SIMPLE [] -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain -select a.*,b.d d1,c.d d2 from - t1_n79 a join t2_n48 b on (a.id1 = b.id) - join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n79 -PREHOOK: Input: default@t2_n48 -#### A masked pattern was here #### -POSTHOOK: query: explain -select a.*,b.d d1,c.d d2 from - t1_n79 a join t2_n48 b on (a.id1 = b.id) - join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n79 -POSTHOOK: Input: default@t2_n48 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: (id1 is not null and id2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (id1 is not null and id2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id1 (type: string), id2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: c - filterExpr: (d <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (d <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: d (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int) - TableScan - alias: b - filterExpr: ((d <= 1) and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id (type: string), d (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col0 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col0 (type: string) - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col4 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: explain -select * from ( -select a.*,b.d d1,c.d d2 from - t1_n79 a join t2_n48 b on (a.id1 = b.id) - join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 -) z where d1 > 1 or d2 > 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n79 -PREHOOK: Input: default@t2_n48 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from ( -select a.*,b.d d1,c.d d2 from - t1_n79 a join t2_n48 b on (a.id1 = b.id) - join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 -) z where d1 > 1 or d2 > 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n79 -POSTHOOK: Input: default@t2_n48 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: (id1 is not null and id2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (id1 is not null and id2 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id1 (type: string), id2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: b - filterExpr: ((d <= 1) and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((d <= 1) and id is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: id (type: string), d (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col0 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col0 (type: string) - Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: int) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) - TableScan - alias: c - filterExpr: (d <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (d <= 1) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: d (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: select * from ( -select a.*,b.d d1,c.d d2 from - t1_n79 a join t2_n48 b on (a.id1 = b.id) - join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 -) z where d1 > 1 or d2 > 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n79 -PREHOOK: Input: default@t2_n48 -#### A masked pattern was here #### -POSTHOOK: query: select * from ( -select a.*,b.d d1,c.d d2 from - t1_n79 a join t2_n48 b on (a.id1 = b.id) - join t2_n48 c on (a.id2 = b.id) where b.d <= 1 and c.d <= 1 -) z where d1 > 1 or d2 > 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n79 -POSTHOOK: Input: default@t2_n48 -#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/ppd_join_filter.q.out ql/src/test/results/clientpositive/ppd_join_filter.q.out deleted file mode 100644 index c38867d45d..0000000000 --- ql/src/test/results/clientpositive/ppd_join_filter.q.out +++ /dev/null @@ -1,1434 +0,0 @@ -PREHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` -FROM (SELECT `key` -FROM `default`.`src` -WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` -FROM `default`.`src` -WHERE `key` IS NOT NULL -GROUP BY `key` -HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(key) - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_1:src] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: false - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_0:a] -#### A masked pattern was here #### - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types string:double:double - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 2.0 3.0 -0 2.0 3.0 -0 2.0 3.0 -2 4.0 5.0 -PREHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` -FROM (SELECT `key` -FROM `default`.`src` -WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` -FROM `default`.`src` -WHERE `key` IS NOT NULL -GROUP BY `key` -HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(key) - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_1:src] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: false - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_0:a] -#### A masked pattern was here #### - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types string:double:double - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 2.0 3.0 -0 2.0 3.0 -0 2.0 3.0 -2 4.0 5.0 -PREHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` -FROM (SELECT `key` -FROM `default`.`src` -WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` -FROM `default`.`src` -WHERE `key` IS NOT NULL -GROUP BY `key` -HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(key) - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_1:src] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: false - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_0:a] -#### A masked pattern was here #### - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types string:double:double - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 2.0 3.0 -0 2.0 3.0 -0 2.0 3.0 -2 4.0 5.0 -PREHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain extended select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t4`.`k2`, `t4`.`k3` -FROM (SELECT `key` -FROM `default`.`src` -WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, CAST(MIN(`key`) AS DOUBLE) + 2 AS `k2`, CAST(MIN(`key`) AS DOUBLE) + 3 AS `k3` -FROM `default`.`src` -WHERE `key` IS NOT NULL -GROUP BY `key` -HAVING CAST(MIN(`key`) AS DOUBLE) + 1 < 5) AS `t4` ON `t0`.`key` = `t4`.`key` -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(key) - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_1:src] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 67750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(_col1) + 1.0D) < 5.0D) (type: boolean) - Statistics: Num rows: 83 Data size: 22493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0D) (type: double), (UDFToDouble(_col1) + 3.0D) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: false - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [$hdt$_0:a] -#### A masked pattern was here #### - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 131 Data size: 13493 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types string:double:double - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select a.key, b.k2, b.k3 -from src a -join ( -select key, -min(key) as k, -min(key)+1 as k1, -min(key)+2 as k2, -min(key)+3 as k3 -from src -group by key -) b -on a.key=b.key and b.k1 < 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 2.0 3.0 -0 2.0 3.0 -0 2.0 3.0 -2 4.0 5.0 diff --git ql/src/test/results/clientpositive/ppd_outer_join1.q.out ql/src/test/results/clientpositive/ppd_outer_join1.q.out deleted file mode 100644 index 6aa702634b..0000000000 --- ql/src/test/results/clientpositive/ppd_outer_join1.q.out +++ /dev/null @@ -1,230 +0,0 @@ -PREHOOK: query: EXPLAIN - FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN - FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -PREHOOK: query: EXPLAIN - FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN - FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: FROM - src a - LEFT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 diff --git ql/src/test/results/clientpositive/ppd_outer_join5.q.out ql/src/test/results/clientpositive/ppd_outer_join5.q.out deleted file mode 100644 index e638368eb9..0000000000 --- ql/src/test/results/clientpositive/ppd_outer_join5.q.out +++ /dev/null @@ -1,436 +0,0 @@ -PREHOOK: query: create table t1_n98 (id int, key string, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t1_n98 -POSTHOOK: query: create table t1_n98 (id int, key string, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t1_n98 -PREHOOK: query: create table t2_n61 (id int, key string, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t2_n61 -POSTHOOK: query: create table t2_n61 (id int, key string, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t2_n61 -PREHOOK: query: create table t3_n23 (id int, key string, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t3_n23 -POSTHOOK: query: create table t3_n23 (id int, key string, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t3_n23 -PREHOOK: query: create table t4_n12 (id int, key string, value string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t4_n12 -POSTHOOK: query: create table t4_n12 (id int, key string, value string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t4_n12 -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain select * from t1_n98 full outer join t2_n61 on t1_n98.id=t2_n61.id join t3_n23 on t2_n61.id=t3_n23.id where t3_n23.id=20 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n98 -PREHOOK: Input: default@t2_n61 -PREHOOK: Input: default@t3_n23 -#### A masked pattern was here #### -POSTHOOK: query: explain select * from t1_n98 full outer join t2_n61 on t1_n98.id=t2_n61.id join t3_n23 on t2_n61.id=t3_n23.id where t3_n23.id=20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n98 -POSTHOOK: Input: default@t2_n61 -POSTHOOK: Input: default@t3_n23 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n98 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - TableScan - alias: t2_n61 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - filter predicates: - 0 - 1 {true} - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) - TableScan - alias: t3_n23 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), 20 (type: int), _col3 (type: string), _col4 (type: string), 20 (type: int), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t2_n61.id=t3_n23.id) where t2_n61.id=20 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n98 -PREHOOK: Input: default@t2_n61 -PREHOOK: Input: default@t3_n23 -#### A masked pattern was here #### -POSTHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t2_n61.id=t3_n23.id) where t2_n61.id=20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n98 -POSTHOOK: Input: default@t2_n61 -POSTHOOK: Input: default@t3_n23 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n98 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: t2_n61 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - TableScan - alias: t3_n23 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 20 (type: int), _col0 (type: string), _col1 (type: string), 20 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t1_n98.id=t3_n23.id) where t2_n61.id=20 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n98 -PREHOOK: Input: default@t2_n61 -PREHOOK: Input: default@t3_n23 -#### A masked pattern was here #### -POSTHOOK: query: explain select * from t1_n98 join t2_n61 on (t1_n98.id=t2_n61.id) left outer join t3_n23 on (t1_n98.id=t3_n23.id) where t2_n61.id=20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n98 -POSTHOOK: Input: default@t2_n61 -POSTHOOK: Input: default@t3_n23 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n98 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: t2_n61 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 745 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - TableScan - alias: t3_n23 - filterExpr: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (id = 20) (type: boolean) - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 20 (type: int), key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 20 (type: int), _col0 (type: string), _col1 (type: string), 20 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1118 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: drop table t1_n98 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@t1_n98 -PREHOOK: Output: default@t1_n98 -POSTHOOK: query: drop table t1_n98 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@t1_n98 -POSTHOOK: Output: default@t1_n98 -PREHOOK: query: drop table t2_n61 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@t2_n61 -PREHOOK: Output: default@t2_n61 -POSTHOOK: query: drop table t2_n61 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@t2_n61 -POSTHOOK: Output: default@t2_n61 -PREHOOK: query: drop table t3_n23 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@t3_n23 -PREHOOK: Output: default@t3_n23 -POSTHOOK: query: drop table t3_n23 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@t3_n23 -POSTHOOK: Output: default@t3_n23 -PREHOOK: query: drop table t4_n12 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@t4_n12 -PREHOOK: Output: default@t4_n12 -POSTHOOK: query: drop table t4_n12 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@t4_n12 -POSTHOOK: Output: default@t4_n12 diff --git ql/src/test/results/clientpositive/ppd_random.q.out ql/src/test/results/clientpositive/ppd_random.q.out deleted file mode 100644 index 12a641faec..0000000000 --- ql/src/test/results/clientpositive/ppd_random.q.out +++ /dev/null @@ -1,190 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT src1.c1, src2.c4 -FROM -(SELECT src.key as c1, src.value as c2 from src ) src1 -JOIN -(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 -WHERE rand() > 0.5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT src1.c1, src2.c4 -FROM -(SELECT src.key as c1, src.value as c2 from src ) src1 -JOIN -(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 -WHERE rand() > 0.5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 262 Data size: 46636 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (rand() > 0.5D) (type: boolean) - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT src1.c1, src2.c4 -FROM -(SELECT src.key as c1, src.value as c2 from src ) src1 -JOIN -(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 -WHERE rand() > 0.5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT src1.c1, src2.c4 -FROM -(SELECT src.key as c1, src.value as c2 from src ) src1 -JOIN -(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 -ON src1.c1 = src2.c3 -WHERE rand() > 0.5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 262 Data size: 46636 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (rand() > 0.5D) (type: boolean) - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 87 Data size: 15486 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/ppd_repeated_alias.q.out ql/src/test/results/clientpositive/ppd_repeated_alias.q.out deleted file mode 100644 index 5243db92a6..0000000000 --- ql/src/test/results/clientpositive/ppd_repeated_alias.q.out +++ /dev/null @@ -1,425 +0,0 @@ -PREHOOK: query: drop table pokes_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pokes_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table pokes2_n0 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table pokes2_n0 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table pokes_n0 (foo int, bar int, blah int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pokes_n0 -POSTHOOK: query: create table pokes_n0 (foo int, bar int, blah int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pokes_n0 -PREHOOK: query: create table pokes2_n0 (foo int, bar int, blah int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@pokes2_n0 -POSTHOOK: query: create table pokes2_n0 (foo int, bar int, blah int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@pokes2_n0 -PREHOOK: query: explain -SELECT a.foo as foo1, b.foo as foo2, b.bar -FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b -ON a.foo=b.foo -WHERE b.bar=3 -PREHOOK: type: QUERY -PREHOOK: Input: default@pokes2_n0 -PREHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain -SELECT a.foo as foo1, b.foo as foo2, b.bar -FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b -ON a.foo=b.foo -WHERE b.bar=3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pokes2_n0 -POSTHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: b - filterExpr: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -SELECT * FROM - (SELECT a.foo as foo1, b.foo as foo2, b.bar - FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b - ON a.foo=b.foo) a -WHERE a.bar=3 -PREHOOK: type: QUERY -PREHOOK: Input: default@pokes2_n0 -PREHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain -SELECT * FROM - (SELECT a.foo as foo1, b.foo as foo2, b.bar - FROM pokes_n0 a LEFT OUTER JOIN pokes2_n0 b - ON a.foo=b.foo) a -WHERE a.bar=3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pokes2_n0 -POSTHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: b - filterExpr: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -SELECT * FROM - (SELECT a.foo as foo1, b.foo as foo2, a.bar - FROM pokes_n0 a JOIN pokes2_n0 b - ON a.foo=b.foo) a -WHERE a.bar=3 -PREHOOK: type: QUERY -PREHOOK: Input: default@pokes2_n0 -PREHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain -SELECT * FROM - (SELECT a.foo as foo1, b.foo as foo2, a.bar - FROM pokes_n0 a JOIN pokes2_n0 b - ON a.foo=b.foo) a -WHERE a.bar=3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pokes2_n0 -POSTHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((bar = 3) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: b - filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), 3 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: explain select c.foo, d.bar from (select c.foo, b.bar, c.blah from pokes_n0 c left outer join pokes_n0 b on c.foo=b.foo) c left outer join pokes_n0 d where d.foo=1 and c.bar=2 -PREHOOK: type: QUERY -PREHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain select c.foo, d.bar from (select c.foo, b.bar, c.blah from pokes_n0 c left outer join pokes_n0 b on c.foo=b.foo) c left outer join pokes_n0 d where d.foo=1 and c.bar=2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@pokes_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: c - filterExpr: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: foo is not null (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: b - filterExpr: ((bar = 2) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((bar = 2) and foo is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: foo (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - TableScan - alias: d - filterExpr: (foo = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (foo = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: bar (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: drop table pokes_n0 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pokes_n0 -PREHOOK: Output: default@pokes_n0 -POSTHOOK: query: drop table pokes_n0 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pokes_n0 -POSTHOOK: Output: default@pokes_n0 -PREHOOK: query: drop table pokes2_n0 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@pokes2_n0 -PREHOOK: Output: default@pokes2_n0 -POSTHOOK: query: drop table pokes2_n0 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@pokes2_n0 -POSTHOOK: Output: default@pokes2_n0 diff --git ql/src/test/results/clientpositive/ppd_udf_case.q.out ql/src/test/results/clientpositive/ppd_udf_case.q.out deleted file mode 100644 index fd9024ca07..0000000000 --- ql/src/test/results/clientpositive/ppd_udf_case.q.out +++ /dev/null @@ -1,316 +0,0 @@ -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key = '27') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 3 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), hr (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: b - filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 546000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key = '27') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 3 Data size: 1638 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), hr (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - sort order: ++++ - Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -27 val_27 2008-04-08 11 27 val_27 2008-04-08 11 -27 val_27 2008-04-08 11 27 val_27 2008-04-08 12 -27 val_27 2008-04-08 12 27 val_27 2008-04-08 11 -27 val_27 2008-04-08 12 27 val_27 2008-04-08 12 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = '27') (type: boolean) - Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), hr (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: b - filterExpr: ((key = '27') and (ds = '2008-04-08')) (type: boolean) - Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = '27') (type: boolean) - Statistics: Num rows: 3 Data size: 1086 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), hr (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - null sort order: zzzz - sort order: ++++ - Statistics: Num rows: 9 Data size: 4950 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 9 Data size: 8190 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * -FROM srcpart a JOIN srcpart b -ON a.key = b.key -WHERE a.ds = '2008-04-08' AND - b.ds = '2008-04-08' AND - CASE a.key - WHEN '27' THEN TRUE - WHEN '38' THEN FALSE - ELSE NULL - END -ORDER BY a.key, a.value, a.ds, a.hr, b.key, b.value, b.ds, b.hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -27 val_27 2008-04-08 11 27 val_27 2008-04-08 11 -27 val_27 2008-04-08 11 27 val_27 2008-04-08 12 -27 val_27 2008-04-08 12 27 val_27 2008-04-08 11 -27 val_27 2008-04-08 12 27 val_27 2008-04-08 12 diff --git ql/src/test/results/clientpositive/ppd_udf_col.q.out ql/src/test/results/clientpositive/ppd_udf_col.q.out deleted file mode 100644 index f959d9d5b0..0000000000 --- ql/src/test/results/clientpositive/ppd_udf_col.q.out +++ /dev/null @@ -1,805 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 <= 0.1D) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 0 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), rand() (type: double), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double), (UDFToDouble(value) * 10.0D) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 <= 0.1D) (type: boolean) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 0 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 100.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), rand() (type: double), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) = 100.0D) and ((UDFToDouble(value) * 10.0D) <= 200.0D)) (type: boolean) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double), (UDFToDouble(value) * 10.0D) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 8549 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col2 <= 0.1D) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col2 <= 0.1D) and (_col2 > 0.1D)) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double), (value * 10) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col2 <= 0.1D) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM -( -SELECT key, randum123 -FROM (SELECT *, cast(rand() as double) AS randum123 FROM src WHERE key = 100) a -WHERE randum123 <=0.1)s WHERE s.randum123>0.1 LIMIT 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 100) (type: boolean) - Statistics: Num rows: 2 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col2 <= 0.1D) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 > 0.1D) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 20 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: 20 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, h4 -FROM (SELECT *, cast(rand() as double) AS randum123, hex(4) AS h4 FROM src WHERE key = 100) a -WHERE a.h4 <= 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key = 100) and false) (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), '4' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT key,randum123, v10 -FROM (SELECT *, cast(rand() as double) AS randum123, value*10 AS v10 FROM src WHERE key = 100) a -WHERE a.v10 <= 200 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key = 100) and ((value * 10) <= 200.0D)) (type: boolean) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), rand() (type: double), (value * 10) (type: double) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col3 <= 200.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: double), _col3 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 103 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/ppd_udtf.q.out ql/src/test/results/clientpositive/ppd_udtf.q.out deleted file mode 100644 index a491d4acc0..0000000000 --- ql/src/test/results/clientpositive/ppd_udtf.q.out +++ /dev/null @@ -1,132 +0,0 @@ -PREHOOK: query: explain -SELECT value from ( - select explode(array(key, value)) as (value) from ( - select * FROM src WHERE key > 400 - ) A -) B WHERE value < 450 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -SELECT value from ( - select explode(array(key, value)) as (value) from ( - select * FROM src WHERE key > 400 - ) A -) B WHERE value < 450 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) > 400.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 400.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(key,value) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 318720 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 166 Data size: 318720 Basic stats: COMPLETE Column stats: COMPLETE - function name: explode - Filter Operator - predicate: (UDFToDouble(col) < 450.0D) (type: boolean) - Statistics: Num rows: 55 Data size: 105600 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: col (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT value from ( - select explode(array(key, value)) as (value) from ( - select * FROM src WHERE key > 400 - ) A -) B WHERE value < 450 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT value from ( - select explode(array(key, value)) as (value) from ( - select * FROM src WHERE key > 400 - ) A -) B WHERE value < 450 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -409 -401 -406 -429 -403 -417 -430 -446 -413 -417 -439 -438 -427 -437 -430 -404 -411 -431 -418 -404 -436 -409 -413 -419 -435 -401 -402 -430 -449 -401 -438 -432 -403 -406 -409 -406 -401 -424 -431 -431 -424 -438 -414 -439 -417 -444 -429 -443 -406 -401 -421 -407 -448 -414 -403 diff --git ql/src/test/results/clientpositive/ppd_vc.q.out ql/src/test/results/clientpositive/ppd_vc.q.out deleted file mode 100644 index 9f24333edc..0000000000 --- ql/src/test/results/clientpositive/ppd_vc.q.out +++ /dev/null @@ -1,842 +0,0 @@ -PREHOOK: query: explain extended -select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds`, `hr` -FROM `default`.`srcpart` -WHERE `BLOCK__OFFSET__INSIDE__FILE` < 100 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - filterExpr: (BLOCK__OFFSET__INSIDE__FILE < 100L) (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (BLOCK__OFFSET__INSIDE__FILE < 100L) (type: boolean) - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: select * from srcpart where BLOCK__OFFSET__INSIDE__FILE<100 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -238 val_238 2008-04-08 11 -86 val_86 2008-04-08 11 -311 val_311 2008-04-08 11 -27 val_27 2008-04-08 11 -165 val_165 2008-04-08 11 -409 val_409 2008-04-08 11 -255 val_255 2008-04-08 11 -278 val_278 2008-04-08 11 -98 val_98 2008-04-08 11 -238 val_238 2008-04-08 12 -86 val_86 2008-04-08 12 -311 val_311 2008-04-08 12 -27 val_27 2008-04-08 12 -165 val_165 2008-04-08 12 -409 val_409 2008-04-08 12 -255 val_255 2008-04-08 12 -278 val_278 2008-04-08 12 -98 val_98 2008-04-08 12 -238 val_238 2008-04-09 11 -86 val_86 2008-04-09 11 -311 val_311 2008-04-09 11 -27 val_27 2008-04-09 11 -165 val_165 2008-04-09 11 -409 val_409 2008-04-09 11 -255 val_255 2008-04-09 11 -278 val_278 2008-04-09 11 -98 val_98 2008-04-09 11 -238 val_238 2008-04-09 12 -86 val_86 2008-04-09 12 -311 val_311 2008-04-09 12 -27 val_27 2008-04-09 12 -165 val_165 2008-04-09 12 -409 val_409 2008-04-09 12 -255 val_255 2008-04-09 12 -278 val_278 2008-04-09 12 -98 val_98 2008-04-09 12 -PREHOOK: query: explain extended -select b.* from src a join - (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b - on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: explain extended -select b.* from src a join - (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b - on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t2`.`key`, `t2`.`value`, `t2`.`ds`, `t2`.`hr`, `t2`.`BLOCK__OFFSET__INSIDE__FILE` AS `block__offset__inside__file` -FROM (SELECT `key` -FROM `default`.`src` -WHERE `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, `ds`, `hr`, `BLOCK__OFFSET__INSIDE__FILE` -FROM `default`.`srcpart` -WHERE `BLOCK__OFFSET__INSIDE__FILE` < 50 AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t2`.`ds`, `t2`.`hr`, `t2`.`BLOCK__OFFSET__INSIDE__FILE` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: false - TableScan - alias: srcpart - filterExpr: ((BLOCK__OFFSET__INSIDE__FILE < 50L) and key is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: PARTIAL - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((BLOCK__OFFSET__INSIDE__FILE < 50L) and key is not null) (type: boolean) - Statistics: Num rows: 666 Data size: 363636 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string), BLOCK__OFFSET__INSIDE__FILE (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 666 Data size: 368964 Basic stats: COMPLETE Column stats: PARTIAL - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 666 Data size: 368964 Basic stats: COMPLETE Column stats: PARTIAL - tag: 1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: bigint) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:srcpart] - /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:srcpart] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL - Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - bucketingVersion: 1 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4 - columns.types string,string,string,string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col2 (type: string), _col3 (type: string), _col4 (type: bigint) - null sort order: zzz - numBuckets: -1 - sort order: +++ - Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4 - columns.types string,string,string,string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3,_col4 - columns.types string,string,string,string,bigint - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1053 Data size: 583362 Basic stats: COMPLETE Column stats: PARTIAL -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3,_col4 - columns.types string:string:string:string:bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select b.* from src a join - (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b - on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: select b.* from src a join - (select *,BLOCK__OFFSET__INSIDE__FILE from srcpart where BLOCK__OFFSET__INSIDE__FILE<100) b - on a.key=b.key AND b.BLOCK__OFFSET__INSIDE__FILE<50 order by ds,hr,BLOCK__OFFSET__INSIDE__FILE -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -238 val_238 2008-04-08 11 0 -238 val_238 2008-04-08 11 0 -86 val_86 2008-04-08 11 12 -311 val_311 2008-04-08 11 22 -311 val_311 2008-04-08 11 22 -311 val_311 2008-04-08 11 22 -27 val_27 2008-04-08 11 34 -165 val_165 2008-04-08 11 44 -165 val_165 2008-04-08 11 44 -238 val_238 2008-04-08 12 0 -238 val_238 2008-04-08 12 0 -86 val_86 2008-04-08 12 12 -311 val_311 2008-04-08 12 22 -311 val_311 2008-04-08 12 22 -311 val_311 2008-04-08 12 22 -27 val_27 2008-04-08 12 34 -165 val_165 2008-04-08 12 44 -165 val_165 2008-04-08 12 44 -238 val_238 2008-04-09 11 0 -238 val_238 2008-04-09 11 0 -86 val_86 2008-04-09 11 12 -311 val_311 2008-04-09 11 22 -311 val_311 2008-04-09 11 22 -311 val_311 2008-04-09 11 22 -27 val_27 2008-04-09 11 34 -165 val_165 2008-04-09 11 44 -165 val_165 2008-04-09 11 44 -238 val_238 2008-04-09 12 0 -238 val_238 2008-04-09 12 0 -86 val_86 2008-04-09 12 12 -311 val_311 2008-04-09 12 22 -311 val_311 2008-04-09 12 22 -311 val_311 2008-04-09 12 22 -27 val_27 2008-04-09 12 34 -165 val_165 2008-04-09 12 44 -165 val_165 2008-04-09 12 44 diff --git ql/src/test/results/clientpositive/ppd_windowing1.q.out ql/src/test/results/clientpositive/ppd_windowing1.q.out deleted file mode 100644 index 4b97afeb87..0000000000 --- ql/src/test/results/clientpositive/ppd_windowing1.q.out +++ /dev/null @@ -1,2195 +0,0 @@ -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where cast(key as int) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where cast(key as int) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key) as c1 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 58930 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToInteger(_col0) + 2) (type: int), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where key > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where cast(key as int) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where cast(key as int) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToInteger(key) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key, value) as c1 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToInteger(_col0) + 2) (type: int), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string) - outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col1 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where key > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string) - outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col1 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string) - outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col1 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(key) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string) - outputColumnNames: sum_window_0, _col0 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col1 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 60258 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToInteger(_col1) + 2) (type: int), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) - outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double), _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string, _col2: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col2 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where key > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) - outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double), _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string, _col2: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col2 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToInteger(key) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) - outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double), _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string, _col2: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col2 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+2 as key, sum(key) over(partition by key,value) as c1, sum(value) over(partition by key) as c2 from src)r1 where (cast(key as int) + 1) > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((UDFToInteger(key) + 2) + 1) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) - outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 74036 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double), _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string, _col2: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_1 - arguments: _col2 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 166 Data size: 75364 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToInteger(_col1) + 2) (type: int), _col0 (type: double), sum_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 3320 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, avg(value) over(partition by value) as c2 from src)r1 where key > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key,value) as c1, avg(value) over(partition by value) as c2 from src)r1 where key > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: sum_window_0 (type: double), _col0 (type: string), _col1 (type: string) - outputColumnNames: sum_window_0, _col0, _col1 - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: sum_window_0 (type: double), _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: double), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 227000 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: double, _col1: string, _col2: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col2 ASC NULLS FIRST - partition by: _col2 - raw input shape: - window functions: - window function definition - alias: avg_window_1 - arguments: _col2 - name: avg - window function: GenericUDAFAverageEvaluatorDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 227000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: double), avg_window_1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + 2) as c1 from src)r1 where key > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + 2) as c1 from src)r1 where key > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: (UDFToDouble(key) + UDFToDouble(2)) (type: double) - null sort order: a - sort order: + - Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(2)) (type: double) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: key (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (UDFToDouble(_col0) + UDFToDouble(2)) ASC NULLS FIRST - partition by: (UDFToDouble(_col0) + UDFToDouble(2)) - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 177500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + value) as c1 from src)r1 where key > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, sum(key) over(partition by key + value) as c1 from src)r1 where key > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: (UDFToDouble(key) + UDFToDouble(value)) (type: double) - null sort order: a - sort order: + - Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(value)) (type: double) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: key (type: string), value (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (UDFToDouble(_col0) + UDFToDouble(_col1)) ASC NULLS FIRST - partition by: (UDFToDouble(_col0) + UDFToDouble(_col1)) - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 15770 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key, value) as c1 from src)r1 where (key + value) > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key, value) as c1 from src)r1 where (key + value) > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(_col0) + UDFToDouble(_col1)) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key + value) as c1 from src)r1 where (key + value) > '2' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT key, value, sum(key) over(partition by key + value) as c1 from src)r1 where (key + value) > '2' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: (UDFToDouble(key) + UDFToDouble(value)) (type: double) - null sort order: a - sort order: + - Map-reduce partition columns: (UDFToDouble(key) + UDFToDouble(value)) (type: double) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: key (type: string), value (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (UDFToDouble(_col0) + UDFToDouble(_col1)) ASC NULLS FIRST - partition by: (UDFToDouble(_col0) + UDFToDouble(_col1)) - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(_col0) + UDFToDouble(_col1)) > 2.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+(cast(value as int)) as key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN select * from (SELECT (cast(key as int))+(cast(value as int)) as key, sum(key) over(partition by key) as c1 from src)r1 where key > 2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: sum_window_0 - arguments: _col0 - name: sum - window function: GenericUDAFSumDouble - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - Statistics: Num rows: 500 Data size: 223000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), sum_window_0 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 93000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToInteger(_col0) + UDFToInteger(_col1)) > 2) (type: boolean) - Statistics: Num rows: 166 Data size: 30876 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: (UDFToInteger(_col0) + UDFToInteger(_col1)) (type: int), _col2 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 1992 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out deleted file mode 100644 index 4ae933694d..0000000000 --- ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out +++ /dev/null @@ -1,516 +0,0 @@ -PREHOOK: query: create table tlb1 (id int, fkey int, val string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tlb1 -POSTHOOK: query: create table tlb1 (id int, fkey int, val string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tlb1 -PREHOOK: query: create table tlb2 (fid int, name string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tlb2 -POSTHOOK: query: create table tlb2 (fid int, name string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tlb2 -PREHOOK: query: insert into table tlb1 values(100,1,'abc') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@tlb1 -POSTHOOK: query: insert into table tlb1 values(100,1,'abc') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@tlb1 -POSTHOOK: Lineage: tlb1.fkey SCRIPT [] -POSTHOOK: Lineage: tlb1.id SCRIPT [] -POSTHOOK: Lineage: tlb1.val SCRIPT [] -PREHOOK: query: insert into table tlb1 values(200,1,'efg') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@tlb1 -POSTHOOK: query: insert into table tlb1 values(200,1,'efg') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@tlb1 -POSTHOOK: Lineage: tlb1.fkey SCRIPT [] -POSTHOOK: Lineage: tlb1.id SCRIPT [] -POSTHOOK: Lineage: tlb1.val SCRIPT [] -PREHOOK: query: insert into table tlb2 values(1, 'key1') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@tlb2 -POSTHOOK: query: insert into table tlb2 values(1, 'key1') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@tlb2 -POSTHOOK: Lineage: tlb2.fid SCRIPT [] -POSTHOOK: Lineage: tlb2.name SCRIPT [] -PREHOOK: query: explain -select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -PREHOOK: type: QUERY -PREHOOK: Input: default@tlb1 -PREHOOK: Input: default@tlb2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tlb1 -POSTHOOK: Input: default@tlb2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tlb1 - filterExpr: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: fkey (type: int), id (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - TableScan - alias: aaa - filterExpr: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: fid (type: int), name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -PREHOOK: type: QUERY -PREHOOK: Input: default@tlb1 -PREHOOK: Input: default@tlb2 -#### A masked pattern was here #### -POSTHOOK: query: select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tlb1 -POSTHOOK: Input: default@tlb2 -#### A masked pattern was here #### -200 1 key1 -100 1 key1 -PREHOOK: query: explain -select ddd.id, ddd.fkey, aaa.name, ddd.rnum -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -PREHOOK: type: QUERY -PREHOOK: Input: default@tlb1 -PREHOOK: Input: default@tlb2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select ddd.id, ddd.fkey, aaa.name, ddd.rnum -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tlb1 -POSTHOOK: Input: default@tlb2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tlb1 - filterExpr: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: id (type: int), fkey (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: aa - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col1: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col0, _col1 - raw input shape: - window functions: - window function definition - alias: row_number_window_0 - name: row_number - window function: GenericUDAFRowNumberEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), row_number_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col2 (type: int) - TableScan - alias: aaa - filterExpr: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: fid (type: int), name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col4 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select ddd.id, ddd.fkey, aaa.name, ddd.rnum -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -PREHOOK: type: QUERY -PREHOOK: Input: default@tlb1 -PREHOOK: Input: default@tlb2 -#### A masked pattern was here #### -POSTHOOK: query: select ddd.id, ddd.fkey, aaa.name, ddd.rnum -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tlb1 -POSTHOOK: Input: default@tlb2 -#### A masked pattern was here #### -200 1 key1 1 -100 1 key1 1 -PREHOOK: query: explain -select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -PREHOOK: type: QUERY -PREHOOK: Input: default@tlb1 -PREHOOK: Input: default@tlb2 -#### A masked pattern was here #### -POSTHOOK: query: explain -select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tlb1 -POSTHOOK: Input: default@tlb2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: tlb1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: fkey is not null (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: fkey (type: int), id (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: int), _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - TableScan - alias: aaa - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: fid is not null (type: boolean) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: fid (type: int), name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -PREHOOK: type: QUERY -PREHOOK: Input: default@tlb1 -PREHOOK: Input: default@tlb2 -#### A masked pattern was here #### -POSTHOOK: query: select ddd.id, ddd.fkey, aaa.name -from ( - select id, fkey, - row_number() over (partition by id, fkey) as rnum - from tlb1 group by id, fkey - ) ddd -inner join tlb2 aaa on aaa.fid = ddd.fkey -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tlb1 -POSTHOOK: Input: default@tlb2 -#### A masked pattern was here #### -200 1 key1 -100 1 key1 diff --git ql/src/test/results/clientpositive/push_or.q.out ql/src/test/results/clientpositive/push_or.q.out deleted file mode 100644 index f97df8fa1b..0000000000 --- ql/src/test/results/clientpositive/push_or.q.out +++ /dev/null @@ -1,254 +0,0 @@ -PREHOOK: query: drop table push_or -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table push_or -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table push_or (key int, value string) partitioned by (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@push_or -POSTHOOK: query: create table push_or (key int, value string) partitioned by (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@push_or -PREHOOK: query: insert overwrite table push_or partition (ds='2000-04-08') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@push_or@ds=2000-04-08 -POSTHOOK: query: insert overwrite table push_or partition (ds='2000-04-08') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@push_or@ds=2000-04-08 -POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table push_or partition (ds='2000-04-09') select * from src where key < 20 order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@push_or@ds=2000-04-09 -POSTHOOK: query: insert overwrite table push_or partition (ds='2000-04-09') select * from src where key < 20 order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@push_or@ds=2000-04-09 -POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: push_or PARTITION(ds=2000-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain extended select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@push_or -PREHOOK: Input: default@push_or@ds=2000-04-08 -PREHOOK: Input: default@push_or@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: explain extended select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@push_or -POSTHOOK: Input: default@push_or@ds=2000-04-08 -POSTHOOK: Input: default@push_or@ds=2000-04-09 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value`, `ds` -FROM `default`.`push_or` -WHERE `key` = 5 OR `ds` = '2000-04-09' -ORDER BY `key`, `ds` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: push_or - filterExpr: ((key = 5) or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key = 5) or (ds = '2000-04-09')) (type: boolean) - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string), ds (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: int), _col2 (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-08 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-08 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.push_or - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct push_or { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.push_or - partition_columns ds - partition_columns.types string - serialization.ddl struct push_or { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.push_or - name: default.push_or -#### A masked pattern was here #### - Partition - base file name: ds=2000-04-09 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2000-04-09 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.push_or - numFiles 1 - numRows 20 - partition_columns ds - partition_columns.types string - rawDataSize 160 - serialization.ddl struct push_or { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 180 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.push_or - partition_columns ds - partition_columns.types string - serialization.ddl struct push_or { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.push_or - name: default.push_or - Truncated Path -> Alias: - /push_or/ds=2000-04-08 [push_or] - /push_or/ds=2000-04-09 [push_or] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 40 Data size: 11120 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2 - columns.types int:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds -PREHOOK: type: QUERY -PREHOOK: Input: default@push_or -PREHOOK: Input: default@push_or@ds=2000-04-08 -PREHOOK: Input: default@push_or@ds=2000-04-09 -#### A masked pattern was here #### -POSTHOOK: query: select key, value, ds from push_or where ds='2000-04-09' or key=5 order by key, ds -POSTHOOK: type: QUERY -POSTHOOK: Input: default@push_or -POSTHOOK: Input: default@push_or@ds=2000-04-08 -POSTHOOK: Input: default@push_or@ds=2000-04-09 -#### A masked pattern was here #### -0 val_0 2000-04-09 -0 val_0 2000-04-09 -0 val_0 2000-04-09 -2 val_2 2000-04-09 -4 val_4 2000-04-09 -5 val_5 2000-04-08 -5 val_5 2000-04-08 -5 val_5 2000-04-08 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -5 val_5 2000-04-09 -8 val_8 2000-04-09 -9 val_9 2000-04-09 -10 val_10 2000-04-09 -11 val_11 2000-04-09 -12 val_12 2000-04-09 -12 val_12 2000-04-09 -15 val_15 2000-04-09 -15 val_15 2000-04-09 -17 val_17 2000-04-09 -18 val_18 2000-04-09 -18 val_18 2000-04-09 -19 val_19 2000-04-09 diff --git ql/src/test/results/clientpositive/query_result_fileformat.q.out ql/src/test/results/clientpositive/query_result_fileformat.q.out deleted file mode 100644 index 2ff3564bad..0000000000 --- ql/src/test/results/clientpositive/query_result_fileformat.q.out +++ /dev/null @@ -1,240 +0,0 @@ -PREHOOK: query: create table nzhang_test1 stored as sequencefile as select 'key1' as key, 'value -1 - -http://asdf' value from src limit 1 -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@nzhang_test1 -POSTHOOK: query: create table nzhang_test1 stored as sequencefile as select 'key1' as key, 'value -1 - -http://asdf' value from src limit 1 -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nzhang_test1 -POSTHOOK: Lineage: nzhang_test1.key SIMPLE [] -POSTHOOK: Lineage: nzhang_test1.value SIMPLE [] -PREHOOK: query: select * from nzhang_test1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: select * from nzhang_test1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -key1 value -1 - -http://asdf -PREHOOK: query: select count(*) from nzhang_test1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from nzhang_test1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -1 -PREHOOK: query: explain vectorization detail -select * from nzhang_test1 where key='key1' -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization detail -select * from nzhang_test1 where key='key1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nzhang_test1 - filterExpr: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct] - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterStringGroupColEqualStringScalar(col 0:string, val key1) - predicate: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'key1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [3, 1] - selectExpressions: ConstantVectorExpression(val key1) -> 3:string - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.row.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - rowBatchContext: - dataColumnCount: 2 - includeColumns: [0, 1] - dataColumns: key:string, value:string - partitionColumnCount: 0 - scratchColumnTypeNames: [string] - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from nzhang_test1 where key='key1' -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: select * from nzhang_test1 where key='key1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -key1 value -1 - -http://asdf -PREHOOK: query: select * from nzhang_test1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: select * from nzhang_test1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -key1 value -1 - -http://asdf -PREHOOK: query: select count(*) from nzhang_test1 -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from nzhang_test1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -1 -PREHOOK: query: explain vectorization detail -select * from nzhang_test1 where key='key1' -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: explain vectorization detail -select * from nzhang_test1 where key='key1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: nzhang_test1 - filterExpr: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true - vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct] - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: FilterStringGroupColEqualStringScalar(col 0:string, val key1) - predicate: (key = 'key1') (type: boolean) - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'key1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [3, 1] - selectExpressions: ConstantVectorExpression(val key1) -> 3:string - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.row.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - rowBatchContext: - dataColumnCount: 2 - includeColumns: [0, 1] - dataColumns: key:string, value:string - partitionColumnCount: 0 - scratchColumnTypeNames: [string] - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from nzhang_test1 where key='key1' -PREHOOK: type: QUERY -PREHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -POSTHOOK: query: select * from nzhang_test1 where key='key1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@nzhang_test1 -#### A masked pattern was here #### -key1 value -1 - -http://asdf diff --git ql/src/test/results/clientpositive/quotedid_basic.q.out ql/src/test/results/clientpositive/quotedid_basic.q.out deleted file mode 100644 index e985054956..0000000000 --- ql/src/test/results/clientpositive/quotedid_basic.q.out +++ /dev/null @@ -1,521 +0,0 @@ -PREHOOK: query: create table t1_n7(`x+1` string, `y&y` string, `!@#$%^&*()_q` string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t1_n7 -POSTHOOK: query: create table t1_n7(`x+1` string, `y&y` string, `!@#$%^&*()_q` string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t1_n7 -PREHOOK: query: describe t1_n7 -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@t1_n7 -POSTHOOK: query: describe t1_n7 -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@t1_n7 -x+1 string -y&y string -!@#$%^&*()_q string -PREHOOK: query: select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -POSTHOOK: query: select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: t1_n7 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: x+1 (type: string), y&y (type: string), !@#$%^&*()_q (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - ListSink - -PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n7 - filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: x+1 (type: string), y&y (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q` from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n7 - filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: x+1 (type: string), y&y (type: string) - outputColumnNames: x+1, y&y - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: x+1 (type: string), y&y (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) -from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -POSTHOOK: query: explain select `x+1`, `y&y`, `!@#$%^&*()_q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) -from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&y`, `!@#$%^&*()_q` having `!@#$%^&*()_q` = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n7 - filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: x+1 (type: string), y&y (type: string) - outputColumnNames: x+1, y&y - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: x+1 (type: string), y&y (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: '1' (type: string), _col1 (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: '1' (type: string) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS LAST - partition by: '1' - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col1 - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '1' (type: string), rank_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select `X+1`, `Y&y`, `!@#$%^&*()_Q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) -from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&Y`, `!@#$%^&*()_q` having `!@#$%^&*()_Q` = '1' -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -POSTHOOK: query: explain select `X+1`, `Y&y`, `!@#$%^&*()_Q`, rank() over(partition by `!@#$%^&*()_q` order by `y&y`) -from t1_n7 where `!@#$%^&*()_q` = '1' group by `x+1`, `y&Y`, `!@#$%^&*()_q` having `!@#$%^&*()_Q` = '1' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n7 - filterExpr: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q = '1') (type: boolean) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: x+1 (type: string), y&y (type: string) - outputColumnNames: x+1, y&y - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: x+1 (type: string), y&y (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: '1' (type: string), _col1 (type: string) - null sort order: az - sort order: ++ - Map-reduce partition columns: '1' (type: string) - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS LAST - partition by: '1' - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col1 - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '1' (type: string), rank_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: create table `t4```(`x+1``` string, `y&y` string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t4` -POSTHOOK: query: create table `t4```(`x+1``` string, `y&y` string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t4` -PREHOOK: query: describe `t4``` -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@t4` -POSTHOOK: query: describe `t4``` -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@t4` -x+1` string -y&y string -PREHOOK: query: insert into table `t4``` select * from src -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@t4` -POSTHOOK: query: insert into table `t4``` select * from src -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@t4` -POSTHOOK: Lineage: t4`.x+1` SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: t4`.y&y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) -from `t4``` where `x+1``` = '10' group by `x+1```, `y&y` having `x+1``` = '10' -PREHOOK: type: QUERY -PREHOOK: Input: default@t4` -#### A masked pattern was here #### -POSTHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) -from `t4``` where `x+1``` = '10' group by `x+1```, `y&y` having `x+1``` = '10' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t4` -#### A masked pattern was here #### -10 val_10 1 -PREHOOK: query: create view v1 as -select `x+1```, `y&y` -from `t4``` where `x+1``` < '200' -PREHOOK: type: CREATEVIEW -PREHOOK: Input: default@t4` -PREHOOK: Output: database:default -PREHOOK: Output: default@v1 -POSTHOOK: query: create view v1 as -select `x+1```, `y&y` -from `t4``` where `x+1``` < '200' -POSTHOOK: type: CREATEVIEW -POSTHOOK: Input: default@t4` -POSTHOOK: Output: database:default -POSTHOOK: Output: default@v1 -POSTHOOK: Lineage: v1.x+1` SIMPLE [(t4`)t4`.FieldSchema(name:x+1`, type:string, comment:null), ] -POSTHOOK: Lineage: v1.y&y SIMPLE [(t4`)t4`.FieldSchema(name:y&y, type:string, comment:null), ] -PREHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) -from v1 -group by `x+1```, `y&y` -PREHOOK: type: QUERY -PREHOOK: Input: default@t4` -PREHOOK: Input: default@v1 -#### A masked pattern was here #### -POSTHOOK: query: select `x+1```, `y&y`, rank() over(partition by `x+1``` order by `y&y`) -from v1 -group by `x+1```, `y&y` -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t4` -POSTHOOK: Input: default@v1 -#### A masked pattern was here #### -0 val_0 1 -10 val_10 1 -100 val_100 1 -103 val_103 1 -104 val_104 1 -105 val_105 1 -11 val_11 1 -111 val_111 1 -113 val_113 1 -114 val_114 1 -116 val_116 1 -118 val_118 1 -119 val_119 1 -12 val_12 1 -120 val_120 1 -125 val_125 1 -126 val_126 1 -128 val_128 1 -129 val_129 1 -131 val_131 1 -133 val_133 1 -134 val_134 1 -136 val_136 1 -137 val_137 1 -138 val_138 1 -143 val_143 1 -145 val_145 1 -146 val_146 1 -149 val_149 1 -15 val_15 1 -150 val_150 1 -152 val_152 1 -153 val_153 1 -155 val_155 1 -156 val_156 1 -157 val_157 1 -158 val_158 1 -160 val_160 1 -162 val_162 1 -163 val_163 1 -164 val_164 1 -165 val_165 1 -166 val_166 1 -167 val_167 1 -168 val_168 1 -169 val_169 1 -17 val_17 1 -170 val_170 1 -172 val_172 1 -174 val_174 1 -175 val_175 1 -176 val_176 1 -177 val_177 1 -178 val_178 1 -179 val_179 1 -18 val_18 1 -180 val_180 1 -181 val_181 1 -183 val_183 1 -186 val_186 1 -187 val_187 1 -189 val_189 1 -19 val_19 1 -190 val_190 1 -191 val_191 1 -192 val_192 1 -193 val_193 1 -194 val_194 1 -195 val_195 1 -196 val_196 1 -197 val_197 1 -199 val_199 1 -2 val_2 1 -20 val_20 1 diff --git ql/src/test/results/clientpositive/quotedid_skew.q.out ql/src/test/results/clientpositive/quotedid_skew.q.out deleted file mode 100644 index 051462fc9e..0000000000 --- ql/src/test/results/clientpositive/quotedid_skew.q.out +++ /dev/null @@ -1,193 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n46(`!@#$%^&*()_q` string, `y&y` string) -SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n46 -POSTHOOK: query: CREATE TABLE T1_n46(`!@#$%^&*()_q` string, `y&y` string) -SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n46 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n46 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n46 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n46 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n46 -PREHOOK: query: CREATE TABLE T2_n28(`!@#$%^&*()_q` string, `y&y` string) -SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n28 -POSTHOOK: query: CREATE TABLE T2_n28(`!@#$%^&*()_q` string, `y&y` string) -SKEWED BY (`!@#$%^&*()_q`) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n28 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T2_n28 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n28 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T2_n28 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n28 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n46 a JOIN T2_n28 b ON a. `!@#$%^&*()_q` = b. `!@#$%^&*()_q` -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n46 -PREHOOK: Input: default@t2_n28 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n46 a JOIN T2_n28 b ON a. `!@#$%^&*()_q` = b. `!@#$%^&*()_q` -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n46 -POSTHOOK: Input: default@t2_n28 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-4 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: !@#$%^&*()_q is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q is not null and (!@#$%^&*()_q = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: !@#$%^&*()_q (type: string), y&y (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: !@#$%^&*()_q is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q is not null and (!@#$%^&*()_q = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: !@#$%^&*()_q (type: string), y&y (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q is not null and (not (!@#$%^&*()_q = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: !@#$%^&*()_q (type: string), y&y (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (!@#$%^&*()_q is not null and (not (!@#$%^&*()_q = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: !@#$%^&*()_q (type: string), y&y (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/rand_partitionpruner1.q.out ql/src/test/results/clientpositive/rand_partitionpruner1.q.out deleted file mode 100644 index a5a05aae45..0000000000 --- ql/src/test/results/clientpositive/rand_partitionpruner1.q.out +++ /dev/null @@ -1,180 +0,0 @@ -PREHOOK: query: explain extended select * from src where rand(1) < 0.1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain extended select * from src where rand(1) < 0.1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT `key`, `value` -FROM `default`.`src` -WHERE RAND(1) < 0.1 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (rand(1) < 0.1D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Execution mode: vectorized - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [src] - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from src where rand(1) < 0.1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * from src where rand(1) < 0.1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -409 val_409 -429 val_429 -209 val_209 -153 val_153 -203 val_203 -170 val_170 -489 val_489 -378 val_378 -221 val_221 -498 val_498 -469 val_469 -176 val_176 -176 val_176 -384 val_384 -217 val_217 -431 val_431 -51 val_51 -288 val_288 -457 val_457 -197 val_197 -77 val_77 -138 val_138 -277 val_277 -224 val_224 -309 val_309 -389 val_389 -331 val_331 -317 val_317 -336 val_336 -42 val_42 -458 val_458 -78 val_78 -453 val_453 -74 val_74 -103 val_103 -467 val_467 -202 val_202 -469 val_469 -44 val_44 -454 val_454 -70 val_70 -491 val_491 -199 val_199 -169 val_169 -310 val_310 -233 val_233 -133 val_133 -26 val_26 -134 val_134 -18 val_18 -298 val_298 -348 val_348 -469 val_469 -37 val_37 -152 val_152 -400 val_400 diff --git ql/src/test/results/clientpositive/rand_partitionpruner2.q.out ql/src/test/results/clientpositive/rand_partitionpruner2.q.out deleted file mode 100644 index e80c298bdb..0000000000 --- ql/src/test/results/clientpositive/rand_partitionpruner2.q.out +++ /dev/null @@ -1,620 +0,0 @@ -PREHOOK: query: create table tmptable_n1(key string, value string, hr string, ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmptable_n1 -POSTHOOK: query: create table tmptable_n1(key string, value string, hr string, ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmptable_n1 -PREHOOK: query: explain extended -insert overwrite table tmptable_n1 -select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Output: default@tmptable_n1 -POSTHOOK: query: explain extended -insert overwrite table tmptable_n1 -select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Output: default@tmptable_n1 -OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` -FROM `default`.`srcpart` -WHERE RAND(1) < 0.1 AND `ds` = '2008-04-08' -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1000 Data size: 362000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (rand(1) < 0.1D) (type: boolean) - Statistics: Num rows: 333 Data size: 120546 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - outputColumnNames: key, value, hr, ds - Statistics: Num rows: 333 Data size: 151848 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(hr, 'hll'), compute_stats(ds, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [a] - /srcpart/ds=2008-04-08/hr=12 [a] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types struct:struct:struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n1 - - Stage: Stage-2 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value, hr, ds - Column Types: string, string, string, string - Table: default.tmptable_n1 - Is Table Level Stats: true - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n1 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n1 - name: default.tmptable_n1 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n1 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value,hr,ds - columns.comments - columns.types string:string:string:string -#### A masked pattern was here #### - name default.tmptable_n1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct tmptable_n1 { string key, string value, string hr, string ds} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n1 - name: default.tmptable_n1 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: insert overwrite table tmptable_n1 -select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Output: default@tmptable_n1 -POSTHOOK: query: insert overwrite table tmptable_n1 -select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Output: default@tmptable_n1 -POSTHOOK: Lineage: tmptable_n1.ds SIMPLE [(srcpart)a.FieldSchema(name:hr, type:string, comment:null), ] -POSTHOOK: Lineage: tmptable_n1.hr SIMPLE [] -POSTHOOK: Lineage: tmptable_n1.key SIMPLE [(srcpart)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable_n1.value SIMPLE [(srcpart)a.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from tmptable_n1 x sort by x.key,x.value,x.ds,x.hr -PREHOOK: type: QUERY -PREHOOK: Input: default@tmptable_n1 -#### A masked pattern was here #### -POSTHOOK: query: select * from tmptable_n1 x sort by x.key,x.value,x.ds,x.hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmptable_n1 -#### A masked pattern was here #### -103 val_103 2008-04-08 11 -118 val_118 2008-04-08 12 -119 val_119 2008-04-08 12 -119 val_119 2008-04-08 12 -126 val_126 2008-04-08 12 -131 val_131 2008-04-08 12 -133 val_133 2008-04-08 11 -134 val_134 2008-04-08 11 -138 val_138 2008-04-08 11 -143 val_143 2008-04-08 12 -152 val_152 2008-04-08 11 -153 val_153 2008-04-08 11 -162 val_162 2008-04-08 12 -169 val_169 2008-04-08 11 -170 val_170 2008-04-08 11 -175 val_175 2008-04-08 12 -176 val_176 2008-04-08 11 -176 val_176 2008-04-08 11 -18 val_18 2008-04-08 11 -18 val_18 2008-04-08 12 -191 val_191 2008-04-08 12 -197 val_197 2008-04-08 11 -199 val_199 2008-04-08 11 -200 val_200 2008-04-08 12 -201 val_201 2008-04-08 12 -202 val_202 2008-04-08 11 -203 val_203 2008-04-08 11 -209 val_209 2008-04-08 11 -214 val_214 2008-04-08 12 -217 val_217 2008-04-08 11 -218 val_218 2008-04-08 12 -221 val_221 2008-04-08 11 -223 val_223 2008-04-08 12 -224 val_224 2008-04-08 11 -229 val_229 2008-04-08 12 -230 val_230 2008-04-08 12 -233 val_233 2008-04-08 11 -233 val_233 2008-04-08 12 -237 val_237 2008-04-08 12 -238 val_238 2008-04-08 12 -256 val_256 2008-04-08 12 -26 val_26 2008-04-08 11 -265 val_265 2008-04-08 12 -273 val_273 2008-04-08 12 -277 val_277 2008-04-08 11 -277 val_277 2008-04-08 12 -280 val_280 2008-04-08 12 -286 val_286 2008-04-08 12 -288 val_288 2008-04-08 11 -298 val_298 2008-04-08 11 -309 val_309 2008-04-08 11 -309 val_309 2008-04-08 12 -310 val_310 2008-04-08 11 -317 val_317 2008-04-08 11 -322 val_322 2008-04-08 12 -323 val_323 2008-04-08 12 -325 val_325 2008-04-08 12 -331 val_331 2008-04-08 11 -332 val_332 2008-04-08 12 -336 val_336 2008-04-08 11 -336 val_336 2008-04-08 12 -339 val_339 2008-04-08 12 -341 val_341 2008-04-08 12 -342 val_342 2008-04-08 12 -348 val_348 2008-04-08 11 -348 val_348 2008-04-08 12 -35 val_35 2008-04-08 12 -364 val_364 2008-04-08 12 -37 val_37 2008-04-08 11 -378 val_378 2008-04-08 11 -384 val_384 2008-04-08 11 -389 val_389 2008-04-08 11 -400 val_400 2008-04-08 11 -403 val_403 2008-04-08 12 -407 val_407 2008-04-08 12 -409 val_409 2008-04-08 11 -417 val_417 2008-04-08 12 -42 val_42 2008-04-08 11 -424 val_424 2008-04-08 12 -429 val_429 2008-04-08 11 -429 val_429 2008-04-08 12 -430 val_430 2008-04-08 12 -431 val_431 2008-04-08 11 -432 val_432 2008-04-08 12 -44 val_44 2008-04-08 11 -453 val_453 2008-04-08 11 -454 val_454 2008-04-08 11 -457 val_457 2008-04-08 11 -457 val_457 2008-04-08 12 -458 val_458 2008-04-08 11 -466 val_466 2008-04-08 12 -467 val_467 2008-04-08 11 -469 val_469 2008-04-08 11 -469 val_469 2008-04-08 11 -469 val_469 2008-04-08 11 -47 val_47 2008-04-08 12 -470 val_470 2008-04-08 12 -489 val_489 2008-04-08 11 -491 val_491 2008-04-08 11 -496 val_496 2008-04-08 12 -498 val_498 2008-04-08 11 -498 val_498 2008-04-08 12 -51 val_51 2008-04-08 11 -58 val_58 2008-04-08 12 -70 val_70 2008-04-08 11 -72 val_72 2008-04-08 12 -74 val_74 2008-04-08 11 -77 val_77 2008-04-08 11 -77 val_77 2008-04-08 12 -78 val_78 2008-04-08 11 -82 val_82 2008-04-08 12 -87 val_87 2008-04-08 12 -90 val_90 2008-04-08 12 -97 val_97 2008-04-08 12 -97 val_97 2008-04-08 12 -98 val_98 2008-04-08 12 diff --git ql/src/test/results/clientpositive/rcfile_null_value.q.out ql/src/test/results/clientpositive/rcfile_null_value.q.out deleted file mode 100644 index 5a4a1f4da8..0000000000 --- ql/src/test/results/clientpositive/rcfile_null_value.q.out +++ /dev/null @@ -1,272 +0,0 @@ -PREHOOK: query: CREATE TABLE src1_rc(key STRING, value STRING) STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src1_rc -POSTHOOK: query: CREATE TABLE src1_rc(key STRING, value STRING) STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src1_rc -PREHOOK: query: INSERT OVERWRITE TABLE src1_rc SELECT * FROM src1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src1 -PREHOOK: Output: default@src1_rc -POSTHOOK: query: INSERT OVERWRITE TABLE src1_rc SELECT * FROM src1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1 -POSTHOOK: Output: default@src1_rc -POSTHOOK: Lineage: src1_rc.key SIMPLE [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src1_rc.value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: SELECT * FROM src1_rc -PREHOOK: type: QUERY -PREHOOK: Input: default@src1_rc -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM src1_rc -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src1_rc -#### A masked pattern was here #### -238 val_238 - -311 val_311 - val_27 - val_165 - val_409 -255 val_255 -278 val_278 -98 val_98 - val_484 - val_265 - val_193 -401 val_401 -150 val_150 -273 val_273 -224 -369 -66 val_66 -128 -213 val_213 -146 val_146 -406 val_406 - - - -PREHOOK: query: CREATE TABLE dest1_rc(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS RCFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest1_rc -POSTHOOK: query: CREATE TABLE dest1_rc(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS RCFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest1_rc -PREHOOK: query: EXPLAIN -FROM ( - FROM - ( - FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 - ) a - RIGHT OUTER JOIN - ( - FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 - ) b - ON (a.c1 = b.c3) - SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 -) c -INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1_rc -POSTHOOK: query: EXPLAIN -FROM ( - FROM - ( - FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 - ) a - RIGHT OUTER JOIN - ( - FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 - ) b - ON (a.c1 = b.c3) - SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 -) c -INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1_rc -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: src2 - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.dest1_rc - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: c1, c2, c3, c4 - Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat - output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat - serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe - name: default.dest1_rc - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: c1, c2, c3, c4 - Column Types: int, string, int, string - Table: default.dest1_rc - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct), _col2 (type: struct), _col3 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: FROM ( - FROM - ( - FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 - ) a - RIGHT OUTER JOIN - ( - FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 - ) b - ON (a.c1 = b.c3) - SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 -) c -INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@dest1_rc -POSTHOOK: query: FROM ( - FROM - ( - FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 - ) a - RIGHT OUTER JOIN - ( - FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 - ) b - ON (a.c1 = b.c3) - SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 -) c -INSERT OVERWRITE TABLE dest1_rc SELECT c.c1, c.c2, c.c3, c.c4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@dest1_rc -POSTHOOK: Lineage: dest1_rc.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_rc.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_rc.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1_rc.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: SELECT dest1_rc.* FROM dest1_rc -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1_rc -#### A masked pattern was here #### -POSTHOOK: query: SELECT dest1_rc.* FROM dest1_rc -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1_rc -#### A masked pattern was here #### -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -NULL NULL 20 val_20 -NULL NULL 24 val_24 -NULL NULL 24 val_24 diff --git ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out deleted file mode 100644 index 557e1fa513..0000000000 --- ql/src/test/results/clientpositive/reduce_deduplicate_exclude_join.q.out +++ /dev/null @@ -1,101 +0,0 @@ -PREHOOK: query: explain select * from (select * from src cluster by key) a join src b on a.key = b.key limit 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select * from (select * from src cluster by key) a join src b on a.key = b.key limit 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-5 depends on stages: Stage-1 - Stage-4 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - b - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 key (type: string) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: 1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out deleted file mode 100644 index 3740f7a94a..0000000000 --- ql/src/test/results/clientpositive/reduce_deduplicate_extended2.q.out +++ /dev/null @@ -1,1085 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM src f -JOIN src g ON (f.key = g.key AND f.value = g.value) -GROUP BY g.value, f.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM src f -JOIN src g ON (f.key = g.key AND f.value = g.value) -GROUP BY g.value, f.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: f - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: g - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT g.key, f.value -FROM src f -JOIN src g ON (f.key = g.key AND f.value = g.value) -GROUP BY g.key, f.value -ORDER BY f.value, g.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT g.key, f.value -FROM src f -JOIN src g ON (f.key = g.key AND f.value = g.value) -GROUP BY g.key, f.value -ORDER BY f.value, g.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: f - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: g - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string), _col0 (type: string) - 1 _col1 (type: string), _col0 (type: string) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col1 (type: string), _col2 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM src f -JOIN ( - SELECT key, value - FROM src - GROUP BY key, value) g -ON (f.key = g.key AND f.value = g.value) -GROUP BY g.value, f.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM src f -JOIN ( - SELECT key, value - FROM src - GROUP BY key, value) g -ON (f.key = g.key AND f.value = g.value) -GROUP BY g.value, f.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-1 depends on stages: Stage-3 - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: f - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 197 Data size: 35066 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM ( - SELECT key, value - FROM src - GROUP BY value, key) f -JOIN ( - SELECT key, value - FROM src - GROUP BY key, value) g -ON (f.key = g.key AND f.value = g.value) -GROUP BY g.value, f.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM ( - SELECT key, value - FROM src - GROUP BY value, key) f -JOIN ( - SELECT key, value - FROM src - GROUP BY key, value) g -ON (f.key = g.key AND f.value = g.value) -GROUP BY g.value, f.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2 - Stage-4 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col3 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM ( - SELECT value - FROM src - GROUP BY value) g -JOIN ( - SELECT key - FROM src - GROUP BY key) f -GROUP BY g.value, f.key -ORDER BY f.key desc, g.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT f.key, g.value -FROM ( - SELECT value - FROM src - GROUP BY value) g -JOIN ( - SELECT key - FROM src - GROUP BY key) f -GROUP BY g.value, f.key -ORDER BY f.key desc, g.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2 - Stage-4 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: -+ - Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 62500 Data size: 11125000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 22750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT x.key, x.value -FROM ( - SELECT f.key, g.value - FROM ( - SELECT key, value - FROM src - GROUP BY key, value) f - JOIN ( - SELECT key, value - FROM src - GROUP BY value, key) g - ON (f.key = g.key AND f.value = g.value) - GROUP BY g.value, f.key -UNION ALL - SELECT f.key, g.value - FROM ( - SELECT key, value - FROM src - GROUP BY value, key) f - JOIN ( - SELECT key, value - FROM src - GROUP BY key, value) g - ON (f.key = g.key AND f.value = g.value) - GROUP BY f.key, g.value -) x -ORDER BY x.value desc, x.key desc -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT x.key, x.value -FROM ( - SELECT f.key, g.value - FROM ( - SELECT key, value - FROM src - GROUP BY key, value) f - JOIN ( - SELECT key, value - FROM src - GROUP BY value, key) g - ON (f.key = g.key AND f.value = g.value) - GROUP BY g.value, f.key -UNION ALL - SELECT f.key, g.value - FROM ( - SELECT key, value - FROM src - GROUP BY value, key) f - JOIN ( - SELECT key, value - FROM src - GROUP BY key, value) g - ON (f.key = g.key AND f.value = g.value) - GROUP BY f.key, g.value -) x -ORDER BY x.value desc, x.key desc -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3, Stage-8 - Stage-6 is a root stage - Stage-7 depends on stages: Stage-6 - Stage-8 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: value (type: string), key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: string), _col0 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col1 (type: string), _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - null sort order: zz - sort order: -- - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Union - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - null sort order: zz - sort order: -- - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: value (type: string), key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col1 (type: string), _col0 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col1 (type: string), _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/regex_col.q.out ql/src/test/results/clientpositive/regex_col.q.out deleted file mode 100644 index c800910a6b..0000000000 --- ql/src/test/results/clientpositive/regex_col.q.out +++ /dev/null @@ -1,539 +0,0 @@ -PREHOOK: query: EXPLAIN -SELECT * FROM srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: EXPLAIN -SELECT `..` FROM srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT `..` FROM srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 757248 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: EXPLAIN -SELECT srcpart.`..` FROM srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT srcpart.`..` FROM srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 757248 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: EXPLAIN -SELECT `..` FROM srcpart a JOIN srcpart b -ON a.key = b.key AND a.value = b.value -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT `..` FROM srcpart a JOIN srcpart b -ON a.key = b.key AND a.value = b.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: string), _col3 (type: string) - TableScan - alias: b - filterExpr: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2000 Data size: 1092000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: string), _col3 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col2, _col3, _col6, _col7 - Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col2 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 12658 Data size: 9316288 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN -SELECT b.`..` FROM srcpart a JOIN srcpart b -ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 -ORDER BY ds, hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT b.`..` FROM srcpart a JOIN srcpart b -ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 -ORDER BY ds, hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) = 103.0D) and hr is not null and ds is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 103.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) - Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: b - filterExpr: ((UDFToDouble(key) = 103.0D) and hr is not null and ds is not null) (type: boolean) - Statistics: Num rows: 2000 Data size: 910000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 103.0D) (type: boolean) - Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string), _col0 (type: string) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string), _col0 (type: string) - Statistics: Num rows: 1000 Data size: 455000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string), _col2 (type: string), _col0 (type: string) - 1 _col1 (type: string), _col2 (type: string), _col0 (type: string) - outputColumnNames: _col4, _col5 - Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col4 (type: string), _col5 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3164 Data size: 1164352 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT b.`..` FROM srcpart a JOIN srcpart b -ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 -ORDER BY ds, hr -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT b.`..` FROM srcpart a JOIN srcpart b -ON a.key = b.key AND a.hr = b.hr AND a.ds = b.ds AND a.key = 103 -ORDER BY ds, hr -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -2008-04-08 11 -2008-04-08 11 -2008-04-08 11 -2008-04-08 11 -2008-04-08 12 -2008-04-08 12 -2008-04-08 12 -2008-04-08 12 -2008-04-09 11 -2008-04-09 11 -2008-04-09 11 -2008-04-09 11 -2008-04-09 12 -2008-04-09 12 -2008-04-09 12 -2008-04-09 12 -PREHOOK: query: EXPLAIN -SELECT `.e.` FROM srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT `.e.` FROM srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: EXPLAIN -SELECT `d.*` FROM srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT `d.*` FROM srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: EXPLAIN -SELECT `(ds)?+.+` FROM srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT `(ds)?+.+` FROM srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2000 Data size: 724000 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: EXPLAIN -SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 10 - Processor Tree: - ListSink - -PREHOOK: query: SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT `(ds|hr)?+.+` FROM srcpart ORDER BY key, value LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 diff --git ql/src/test/results/clientpositive/router_join_ppr.q.out ql/src/test/results/clientpositive/router_join_ppr.q.out deleted file mode 100644 index 832612f070..0000000000 --- ql/src/test/results/clientpositive/router_join_ppr.q.out +++ /dev/null @@ -1,1292 +0,0 @@ -PREHOOK: query: EXPLAIN EXTENDED - FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED - FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`src` -WHERE `key` < 20 AND `key` > 15) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`srcpart` -WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key AND b.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -17 val_17 17 val_17 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19 -PREHOOK: query: EXPLAIN EXTENDED - FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key AND a.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED - FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key AND a.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`srcpart` -WHERE `key` < 20 AND `key` > 15 AND `ds` = '2008-04-08') AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`src` -WHERE `key` > 15 AND `key` < 20) AS `t2` ON `t0`.`key` = `t2`.`key` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /src [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key AND a.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key AND a.ds = '2008-04-08') - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -17 val_17 17 val_17 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19 -PREHOOK: query: EXPLAIN EXTENDED - FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED - FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`src` -WHERE `key` < 20 AND `key` > 15) AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`srcpart` -WHERE `key` > 15 AND `key` < 20 AND `ds` = '2008-04-08') AS `t2` ON `t0`.`key` = `t2`.`key` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: FROM - src a - RIGHT OUTER JOIN - srcpart b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -17 val_17 17 val_17 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19 -PREHOOK: query: EXPLAIN EXTENDED - FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED - FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -OPTIMIZED SQL: SELECT * -FROM (SELECT `key`, `value` -FROM `default`.`srcpart` -WHERE `key` < 20 AND `key` > 15 AND `ds` = '2008-04-08') AS `t0` -INNER JOIN (SELECT `key`, `value` -FROM `default`.`src` -WHERE `key` > 15 AND `key` < 20) AS `t2` ON `t0`.`key` = `t2`.`key` -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 111 Data size: 19758 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col1 (type: string) - auto parallelism: false - TableScan - alias: b - filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: _col0 (type: string) - null sort order: z - numBuckets: -1 - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /src [$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:a] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: FROM - srcpart a - RIGHT OUTER JOIN - src b - ON (a.key = b.key) - SELECT a.key, a.value, b.key, b.value - WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND a.ds = '2008-04-08' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -17 val_17 17 val_17 -17 val_17 17 val_17 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -18 val_18 18 val_18 -19 val_19 19 val_19 -19 val_19 19 val_19 diff --git ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out deleted file mode 100644 index 406f3d3f82..0000000000 --- ql/src/test/results/clientpositive/runtime_skewjoin_mapjoin_spark.q.out +++ /dev/null @@ -1,451 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n94(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n94 -POSTHOOK: query: CREATE TABLE T1_n94(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n94 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n94 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n94 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n94 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n94 -PREHOOK: query: EXPLAIN -SELECT COUNT(*) FROM - (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a -JOIN - (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b -ON a.key=b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@t1_n94 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT COUNT(*) FROM - (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a -JOIN - (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b -ON a.key=b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@t1_n94 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-19 is a root stage - Stage-14 depends on stages: Stage-19 - Stage-13 depends on stages: Stage-14 , consists of Stage-17, Stage-18, Stage-2 - Stage-17 has a backup stage: Stage-2 - Stage-11 depends on stages: Stage-17 - Stage-10 depends on stages: Stage-2, Stage-11, Stage-12 , consists of Stage-15, Stage-16, Stage-3 - Stage-15 has a backup stage: Stage-3 - Stage-8 depends on stages: Stage-15 - Stage-4 depends on stages: Stage-3, Stage-8, Stage-9 - Stage-16 has a backup stage: Stage-3 - Stage-9 depends on stages: Stage-16 - Stage-3 - Stage-18 has a backup stage: Stage-2 - Stage-12 depends on stages: Stage-18 - Stage-2 - Stage-0 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-19 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_3:t1_n94 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_3:t1_n94 - TableScan - alias: t1_n94 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-14 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-13 - Conditional Operator - - Stage: Stage-17 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:src1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:src1 - TableScan - alias: src1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-10 - Conditional Operator - - Stage: Stage-15 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:src2 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:src2 - TableScan - alias: src2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 665 Data size: 57898 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-16 - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME - TableScan - HashTable Sink Operator - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - alias: src2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 665 Data size: 57898 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col2 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: string) - Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: src2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 665 Data size: 57898 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-18 - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME - TableScan - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-12 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 47850 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: src1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - Statistics: Num rows: 605 Data size: 52635 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT COUNT(*) FROM - (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a -JOIN - (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b -ON a.key=b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@t1_n94 -#### A masked pattern was here #### -POSTHOOK: query: SELECT COUNT(*) FROM - (SELECT src1.key,src1.value FROM src src1 JOIN src src2 ON src1.key=src2.key) a -JOIN - (SELECT src.key,src.value FROM src JOIN T1_n94 ON src.key=T1_n94.key) b -ON a.key=b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@t1_n94 -#### A masked pattern was here #### -3 diff --git ql/src/test/results/clientpositive/sample5.q.out ql/src/test/results/clientpositive/sample5.q.out deleted file mode 100644 index 798392cf09..0000000000 --- ql/src/test/results/clientpositive/sample5.q.out +++ /dev/null @@ -1,664 +0,0 @@ -PREHOOK: query: CREATE TABLE dest1_n69(key INT, value STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest1_n69 -POSTHOOK: query: CREATE TABLE dest1_n69(key INT, value STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest1_n69 -PREHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest1_n69 SELECT s.* - -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s -PREHOOK: type: QUERY -PREHOOK: Input: default@srcbucket -PREHOOK: Output: default@dest1_n69 -POSTHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest1_n69 SELECT s.* - -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcbucket -POSTHOOK: Output: default@dest1_n69 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: (((hash(key) & 2147483647) % 5) = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n69 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n69 - - Stage: Stage-2 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.dest1_n69 - Is Table Level Stats: true - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n69 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n69 - name: default.dest1_n69 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n69 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n69 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n69 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n69 - name: default.dest1_n69 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: INSERT OVERWRITE TABLE dest1_n69 SELECT s.* - -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s -PREHOOK: type: QUERY -PREHOOK: Input: default@srcbucket -PREHOOK: Output: default@dest1_n69 -POSTHOOK: query: INSERT OVERWRITE TABLE dest1_n69 SELECT s.* - -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 5 on key) s -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcbucket -POSTHOOK: Output: default@dest1_n69 -POSTHOOK: Lineage: dest1_n69.key SIMPLE [(srcbucket)s.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest1_n69.value SIMPLE [(srcbucket)s.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: SELECT dest1_n69.* FROM dest1_n69 SORT BY key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1_n69 -#### A masked pattern was here #### -POSTHOOK: query: SELECT dest1_n69.* FROM dest1_n69 SORT BY key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1_n69 -#### A masked pattern was here #### -1 val_2 -103 val_103 -103 val_103 -122 val_123 -122 val_123 -122 val_123 -125 val_125 -125 val_125 -125 val_126 -133 val_133 -133 val_134 -147 val_148 -147 val_148 -155 val_155 -16 val_17 -16 val_17 -161 val_162 -161 val_162 -161 val_162 -161 val_162 -162 val_162 -162 val_163 -163 val_163 -165 val_165 -165 val_165 -165 val_166 -18 val_18 -18 val_18 -194 val_194 -196 val_196 -196 val_197 -196 val_197 -196 val_197 -21 val_22 -21 val_22 -21 val_22 -21 val_22 -222 val_222 -222 val_223 -230 val_230 -230 val_230 -230 val_230 -230 val_230 -230 val_230 -237 val_237 -237 val_237 -238 val_238 -238 val_238 -238 val_239 -24 val_24 -24 val_24 -240 val_241 -246 val_247 -246 val_247 -256 val_256 -256 val_256 -256 val_257 -260 val_260 -260 val_261 -260 val_261 -264 val_265 -264 val_265 -273 val_273 -273 val_273 -273 val_273 -273 val_274 -275 val_275 -275 val_276 -275 val_276 -276 val_277 -278 val_278 -278 val_278 -278 val_279 -288 val_288 -288 val_288 -289 val_289 -289 val_290 -296 val_296 -296 val_297 -302 val_302 -302 val_303 -305 val_305 -305 val_306 -311 val_311 -311 val_311 -311 val_311 -32 val_33 -323 val_323 -323 val_324 -33 val_33 -33 val_34 -332 val_332 -335 val_335 -335 val_336 -335 val_336 -344 val_344 -344 val_344 -344 val_345 -35 val_35 -35 val_35 -35 val_35 -35 val_36 -35 val_36 -35 val_36 -352 val_353 -352 val_353 -355 val_356 -355 val_356 -362 val_362 -366 val_366 -369 val_369 -369 val_369 -369 val_369 -369 val_370 -37 val_37 -37 val_37 -373 val_373 -373 val_374 -379 val_379 -379 val_380 -391 val_392 -391 val_392 -393 val_393 -393 val_394 -393 val_394 -397 val_397 -397 val_397 -405 val_406 -407 val_407 -407 val_408 -407 val_408 -407 val_408 -41 val_41 -410 val_411 -411 val_411 -411 val_412 -416 val_417 -425 val_426 -43 val_43 -432 val_432 -432 val_433 -435 val_435 -435 val_436 -436 val_436 -436 val_437 -439 val_439 -439 val_439 -439 val_440 -439 val_440 -441 val_442 -450 val_451 -450 val_451 -453 val_453 -453 val_454 -454 val_454 -454 val_454 -454 val_454 -454 val_455 -454 val_455 -455 val_455 -455 val_456 -455 val_456 -460 val_460 -466 val_466 -466 val_466 -466 val_466 -469 val_469 -469 val_469 -469 val_469 -469 val_469 -469 val_469 -469 val_470 -470 val_470 -470 val_471 -481 val_481 -481 val_482 -484 val_484 -484 val_485 -492 val_492 -492 val_492 -492 val_493 -492 val_493 -493 val_493 -494 val_494 -494 val_495 -494 val_495 -498 val_498 -498 val_498 -498 val_498 -51 val_51 -51 val_51 -51 val_52 -52 val_53 -52 val_53 -52 val_53 -52 val_53 -53 val_53 -53 val_54 -54 val_54 -61 val_62 -68 val_69 -69 val_69 -69 val_70 -72 val_72 -72 val_72 -8 val_8 -8 val_9 -87 val_87 -87 val_88 -87 val_88 -89 val_90 -89 val_90 -89 val_90 -91 val_92 -93 val_94 -93 val_94 -93 val_94 -96 val_96 diff --git ql/src/test/results/clientpositive/sample7.q.out ql/src/test/results/clientpositive/sample7.q.out deleted file mode 100644 index 9cec21c7ec..0000000000 --- ql/src/test/results/clientpositive/sample7.q.out +++ /dev/null @@ -1,673 +0,0 @@ -PREHOOK: query: CREATE TABLE dest1_n160(key INT, value STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest1_n160 -POSTHOOK: query: CREATE TABLE dest1_n160(key INT, value STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest1_n160 -PREHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest1_n160 SELECT s.* -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s -WHERE s.key > 100 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcbucket -PREHOOK: Output: default@dest1_n160 -POSTHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest1_n160 SELECT s.* -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s -WHERE s.key > 100 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcbucket -POSTHOOK: Output: default@dest1_n160 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - filterExpr: (key > 100) (type: boolean) - Statistics: Num rows: 1000 Data size: 95000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((((hash(key) & 2147483647) % 4) = 0) and (key > 100)) (type: boolean) - Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n160 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: int), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 400 Data size: 38000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - null sort order: - numBuckets: -1 - sort order: - Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: struct), _col1 (type: struct) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: srcbucket - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count 2 - bucket_field_name key - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.srcbucket - numFiles 2 - numRows 1000 - rawDataSize 10603 - serialization.ddl struct srcbucket { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 11603 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcbucket - name: default.srcbucket - Truncated Path -> Alias: - /srcbucket [s] - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1 - columns.types struct:struct - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n160 - - Stage: Stage-2 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: int, string - Table: default.dest1_n160 - Is Table Level Stats: true - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n160 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n160 - name: default.dest1_n160 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n160 - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10002 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.dest1_n160 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest1_n160 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n160 - name: default.dest1_n160 - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: INSERT OVERWRITE TABLE dest1_n160 SELECT s.* -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s -WHERE s.key > 100 -PREHOOK: type: QUERY -PREHOOK: Input: default@srcbucket -PREHOOK: Output: default@dest1_n160 -POSTHOOK: query: INSERT OVERWRITE TABLE dest1_n160 SELECT s.* -FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s -WHERE s.key > 100 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcbucket -POSTHOOK: Output: default@dest1_n160 -POSTHOOK: Lineage: dest1_n160.key SIMPLE [(srcbucket)s.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest1_n160.value SIMPLE [(srcbucket)s.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: SELECT dest1_n160.* FROM dest1_n160 -order by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1_n160 -#### A masked pattern was here #### -POSTHOOK: query: SELECT dest1_n160.* FROM dest1_n160 -order by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1_n160 -#### A masked pattern was here #### -105 val_105 -105 val_106 -105 val_106 -110 val_111 -113 val_113 -113 val_113 -116 val_116 -116 val_117 -117 val_118 -117 val_118 -119 val_119 -119 val_119 -119 val_119 -119 val_120 -119 val_120 -119 val_120 -121 val_122 -121 val_122 -123 val_124 -123 val_124 -126 val_126 -126 val_127 -126 val_127 -134 val_134 -134 val_134 -134 val_135 -137 val_137 -137 val_137 -137 val_138 -153 val_153 -153 val_154 -153 val_154 -156 val_156 -156 val_157 -156 val_157 -157 val_157 -157 val_158 -157 val_158 -158 val_158 -163 val_163 -169 val_169 -169 val_169 -169 val_169 -169 val_169 -177 val_177 -177 val_178 -177 val_178 -178 val_178 -178 val_179 -178 val_179 -184 val_185 -187 val_187 -187 val_187 -187 val_187 -195 val_195 -195 val_195 -197 val_197 -197 val_197 -197 val_198 -206 val_207 -206 val_207 -206 val_207 -208 val_208 -208 val_208 -208 val_208 -221 val_221 -221 val_221 -229 val_229 -229 val_229 -237 val_237 -237 val_237 -243 val_244 -243 val_244 -244 val_244 -244 val_245 -244 val_245 -244 val_245 -249 val_249 -249 val_250 -249 val_250 -252 val_252 -252 val_253 -254 val_255 -256 val_256 -256 val_256 -256 val_257 -266 val_266 -271 val_272 -272 val_272 -272 val_272 -272 val_273 -286 val_286 -286 val_287 -289 val_289 -289 val_290 -292 val_292 -292 val_293 -292 val_293 -304 val_305 -307 val_307 -307 val_307 -308 val_308 -308 val_309 -308 val_309 -315 val_315 -316 val_316 -316 val_316 -316 val_316 -317 val_317 -317 val_317 -317 val_318 -326 val_327 -327 val_327 -327 val_327 -327 val_327 -334 val_335 -336 val_336 -336 val_337 -338 val_338 -338 val_339 -339 val_339 -342 val_342 -342 val_342 -342 val_343 -344 val_344 -344 val_344 -344 val_345 -348 val_348 -348 val_348 -348 val_348 -348 val_348 -348 val_348 -348 val_349 -349 val_350 -349 val_350 -349 val_350 -349 val_350 -352 val_353 -352 val_353 -353 val_353 -353 val_353 -353 val_354 -355 val_356 -355 val_356 -360 val_360 -360 val_361 -362 val_362 -364 val_364 -364 val_365 -369 val_369 -369 val_369 -369 val_369 -369 val_370 -371 val_372 -371 val_372 -371 val_372 -371 val_372 -377 val_377 -378 val_378 -378 val_379 -391 val_392 -391 val_392 -392 val_392 -392 val_393 -392 val_393 -396 val_396 -396 val_396 -396 val_396 -399 val_399 -399 val_399 -399 val_400 -399 val_400 -402 val_402 -402 val_403 -402 val_403 -402 val_403 -404 val_404 -404 val_404 -404 val_405 -404 val_405 -404 val_405 -407 val_407 -407 val_408 -407 val_408 -407 val_408 -408 val_409 -408 val_409 -410 val_411 -417 val_417 -417 val_417 -417 val_417 -419 val_419 -423 val_424 -426 val_427 -427 val_427 -427 val_428 -427 val_428 -440 val_441 -440 val_441 -449 val_449 -452 val_452 -458 val_458 -458 val_458 -463 val_463 -463 val_463 -463 val_464 -466 val_466 -466 val_466 -466 val_466 -472 val_472 -476 val_477 -476 val_477 -478 val_478 -478 val_478 -478 val_479 -478 val_479 -479 val_479 -482 val_482 -482 val_483 -484 val_484 -484 val_485 -497 val_497 -497 val_498 -497 val_498 diff --git ql/src/test/results/clientpositive/sample8.q.out ql/src/test/results/clientpositive/sample8.q.out deleted file mode 100644 index 0431aa7f52..0000000000 --- ql/src/test/results/clientpositive/sample8.q.out +++ /dev/null @@ -1,861 +0,0 @@ -PREHOOK: query: EXPLAIN EXTENDED -SELECT s.* -FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s -JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t -WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN EXTENDED -SELECT s.* -FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s -JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t -WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - filterExpr: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: ((((hash(key) & 2147483647) % 10) = 0) and value is not null and (((hash(key) & 2147483647) % 1) = 0)) (type: boolean) - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: key (type: string), value (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 125 Data size: 22250 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: false - TableScan - alias: t - Statistics: Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: true - predicate: ((((hash(key) & 2147483647) % 1) = 0) and value is not null and (((hash(key) & 2147483647) % 10) = 0)) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - bucketingVersion: 2 - key expressions: key (type: string), value (type: string) - null sort order: zz - numBuckets: -1 - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - bucketing_version 2 - column.name.delimiter , - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [s, t] - /srcpart/ds=2008-04-08/hr=12 [t] - /srcpart/ds=2008-04-09/hr=11 [t] - /srcpart/ds=2008-04-09/hr=12 [t] - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string), value (type: string) - 1 key (type: string), value (type: string) - outputColumnNames: _col0, _col1, _col7, _col8 - Statistics: Num rows: 197 Data size: 70132 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - isSamplingPred: false - predicate: ((_col7 = _col0) and (_col8 = _col1)) (type: boolean) - Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), '11' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - bucketingVersion: 2 - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 49 Data size: 17444 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - bucketing_version -1 - columns _col0,_col1,_col2,_col3 - columns.types string:string:string:string - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT s.key, s.value -FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s -JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t -WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: SELECT s.key, s.value -FROM srcpart TABLESAMPLE (BUCKET 1 OUT OF 1 ON key) s -JOIN srcpart TABLESAMPLE (BUCKET 1 OUT OF 10 ON key) t -WHERE t.key = s.key and t.value = s.value and s.ds='2008-04-08' and s.hr='11' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -149 val_149 -196 val_196 -196 val_196 -196 val_196 -196 val_196 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -219 val_219 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -238 val_238 -258 val_258 -258 val_258 -258 val_258 -258 val_258 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -280 val_280 -285 val_285 -285 val_285 -285 val_285 -285 val_285 -291 val_291 -291 val_291 -291 val_291 -291 val_291 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -298 val_298 -306 val_306 -306 val_306 -306 val_306 -306 val_306 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -37 val_37 -374 val_374 -374 val_374 -374 val_374 -374 val_374 -377 val_377 -377 val_377 -377 val_377 -377 val_377 -394 val_394 -394 val_394 -394 val_394 -394 val_394 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -414 val_414 -444 val_444 -444 val_444 -444 val_444 -444 val_444 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -458 val_458 -485 val_485 -485 val_485 -485 val_485 -485 val_485 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -492 val_492 -66 val_66 -66 val_66 -66 val_66 -66 val_66 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -67 val_67 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -72 val_72 -8 val_8 -8 val_8 -8 val_8 -8 val_8 -86 val_86 -86 val_86 -86 val_86 -86 val_86 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -97 val_97 -PREHOOK: query: EXPLAIN -SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Row Limit Per Split: 100 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Row Limit Per Split: 10 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a JOIN src1 TABLESAMPLE(10 ROWS) b ON a.key=b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -238 val_238 238 val_238 -255 val_255 255 val_255 -278 val_278 278 val_278 -311 val_311 311 val_311 -311 val_311 311 val_311 -98 val_98 98 val_98 -PREHOOK: query: EXPLAIN -SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Row Limit Per Split: 100 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Row Limit Per Split: 10 - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 = _col5) (type: boolean) - Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 19 Data size: 6707 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM src TABLESAMPLE(100 ROWS) a, src1 TABLESAMPLE(10 ROWS) b WHERE a.key=b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -238 val_238 238 val_238 -255 val_255 255 val_255 -278 val_278 278 val_278 -311 val_311 311 val_311 -311 val_311 311 val_311 -98 val_98 98 val_98 diff --git ql/src/test/results/clientpositive/select_as_omitted.q.out ql/src/test/results/clientpositive/select_as_omitted.q.out deleted file mode 100644 index c4c961b8b6..0000000000 --- ql/src/test/results/clientpositive/select_as_omitted.q.out +++ /dev/null @@ -1,80 +0,0 @@ -PREHOOK: query: EXPLAIn -SELECT a, b FROM ( - SELECT key a, value b - FROM src -) src1 -ORDER BY a LIMIT 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIn -SELECT a, b FROM ( - SELECT key a, value b - FROM src -) src1 -ORDER BY a LIMIT 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a, b FROM ( - SELECT key a, value b - FROM src -) src1 -ORDER BY a LIMIT 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT a, b FROM ( - SELECT key a, value b - FROM src -) src1 -ORDER BY a LIMIT 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 diff --git ql/src/test/results/clientpositive/select_column_pruning.q.out ql/src/test/results/clientpositive/select_column_pruning.q.out deleted file mode 100644 index b2dbac1ecf..0000000000 --- ql/src/test/results/clientpositive/select_column_pruning.q.out +++ /dev/null @@ -1,150 +0,0 @@ -PREHOOK: query: CREATE TABLE lv_table1( c1 STRING, c2 ARRAY, c3 INT, c4 CHAR(1), c5 STRING, c6 STRING, c7 STRING, c8 STRING, c9 STRING, c10 STRING, c11 STRING) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@lv_table1 -POSTHOOK: query: CREATE TABLE lv_table1( c1 STRING, c2 ARRAY, c3 INT, c4 CHAR(1), c5 STRING, c6 STRING, c7 STRING, c8 STRING, c9 STRING, c10 STRING, c11 STRING) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@lv_table1 -PREHOOK: query: INSERT OVERWRITE TABLE lv_table1 SELECT 'abc ', array(1,2,3), 100, 't', 'test', 'test', 'test', 'test', 'test', 'test', 'test' FROM src -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@lv_table1 -POSTHOOK: query: INSERT OVERWRITE TABLE lv_table1 SELECT 'abc ', array(1,2,3), 100, 't', 'test', 'test', 'test', 'test', 'test', 'test', 'test' FROM src -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@lv_table1 -POSTHOOK: Lineage: lv_table1.c1 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c10 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c11 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c2 EXPRESSION [] -POSTHOOK: Lineage: lv_table1.c3 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c4 EXPRESSION [] -POSTHOOK: Lineage: lv_table1.c5 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c6 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c7 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c8 SIMPLE [] -POSTHOOK: Lineage: lv_table1.c9 SIMPLE [] -PREHOOK: query: EXPLAIN SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@lv_table1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@lv_table1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: lv_table1 - filterExpr: (c3 = 100) (type: boolean) - Statistics: Num rows: 500 Data size: 800156 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (c3 = 100) (type: boolean) - Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: string), c2 (type: array), c4 (type: char(1)), c5 (type: string), c6 (type: string), c7 (type: string), c8 (type: string), c9 (type: string), c10 (type: string), c11 (type: string) - outputColumnNames: c1, c2, c4, c5, c6, c7, c8, c9, c10, c11 - Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14 - Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col14 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col11 (type: int) - null sort order: zz - sort order: ++ - Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) - Select Operator - expressions: array(1,2,3) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 5 Data size: 8001 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col14 - Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col14 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col11 (type: int) - null sort order: zz - sort order: ++ - Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), VALUE._col2 (type: char(1)), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 10 Data size: 16002 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col11 (type: int) - null sort order: zz - sort order: ++ - Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: array), _col3 (type: char(1)), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: array), 100 (type: int), VALUE._col2 (type: char(1)), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: string), VALUE._col8 (type: string), VALUE._col9 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 1 - Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 1600 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@lv_table1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM lv_table1 LATERAL VIEW explode(array(1,2,3)) myTable AS myCol WHERE c3 = 100 SORT BY c1 ASC, myCol ASC LIMIT 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@lv_table1 -#### A masked pattern was here #### -abc [1,2,3] 100 t test test test test test test test 1 diff --git ql/src/test/results/clientpositive/semijoin2.q.out ql/src/test/results/clientpositive/semijoin2.q.out deleted file mode 100644 index 2a176e65a3..0000000000 --- ql/src/test/results/clientpositive/semijoin2.q.out +++ /dev/null @@ -1,303 +0,0 @@ -PREHOOK: query: CREATE TABLE table_1_n0 (boolean_col_1 BOOLEAN, float_col_2 FLOAT, bigint_col_3 BIGINT, varchar0111_col_4 VARCHAR(111), bigint_col_5 BIGINT, float_col_6 FLOAT, boolean_col_7 BOOLEAN, decimal0101_col_8 DECIMAL(1, 1), decimal0904_col_9 DECIMAL(9, 4), char0112_col_10 CHAR(112), double_col_11 DOUBLE, boolean_col_12 BOOLEAN, double_col_13 DOUBLE, varchar0142_col_14 VARCHAR(142), timestamp_col_15 TIMESTAMP, decimal0502_col_16 DECIMAL(5, 2), smallint_col_25 SMALLINT, decimal3222_col_18 DECIMAL(32, 22), boolean_col_19 BOOLEAN, decimal2012_col_20 DECIMAL(20, 12), char0204_col_21 CHAR(204), double_col_61 DOUBLE, timestamp_col_23 TIMESTAMP, int_col_24 INT, float_col_25 FLOAT, smallint_col_26 SMALLINT, double_col_27 DOUBLE, char0180_col_28 CHAR(180), decimal1503_col_29 DECIMAL(15, 3), timestamp_col_30 TIMESTAMP, smallint_col_31 SMALLINT, decimal2020_col_32 DECIMAL(20, 20), timestamp_col_33 TIMESTAMP, boolean_col_34 BOOLEAN, decimal3025_col_35 DECIMAL(30, 25), decimal3117_col_36 DECIMAL(31, 17), timestamp_col_37 TIMESTAMP, varchar0146_col_38 VARCHAR(146), boolean_col_39 BOOLEAN, double_col_40 DOUBLE, float_col_41 FLOAT, timestamp_col_42 TIMESTAMP, double_col_43 DOUBLE, boolean_col_44 BOOLEAN, timestamp_col_45 TIMESTAMP, tinyint_col_8 TINYINT, int_col_47 INT, decimal0401_col_48 DECIMAL(4, 1), varchar0064_col_49 VARCHAR(64), string_col_50 STRING, double_col_51 DOUBLE, string_col_52 STRING, boolean_col_53 BOOLEAN, int_col_54 INT, boolean_col_55 BOOLEAN, string_col_56 STRING, double_col_57 DOUBLE, varchar0131_col_58 VARCHAR(131), boolean_col_59 BOOLEAN, bigint_col_22 BIGINT, char0184_col_61 CHAR(184), varchar0173_col_62 VARCHAR(173), timestamp_col_63 TIMESTAMP, decimal1709_col_26 DECIMAL(20, 5), timestamp_col_65 TIMESTAMP, timestamp_col_66 TIMESTAMP, timestamp_col_67 TIMESTAMP, boolean_col_68 BOOLEAN, decimal1208_col_20 DECIMAL(33, 11), decimal1605_col_70 DECIMAL(16, 5), varchar0010_col_71 VARCHAR(10), tinyint_col_72 TINYINT, timestamp_col_10 TIMESTAMP, decimal2714_col_74 DECIMAL(27, 14), double_col_75 DOUBLE, boolean_col_76 BOOLEAN, double_col_77 DOUBLE, string_col_78 STRING, boolean_col_79 BOOLEAN, boolean_col_80 BOOLEAN, decimal0803_col_81 DECIMAL(8, 3), decimal1303_col_82 DECIMAL(13, 3), tinyint_col_83 TINYINT, decimal3424_col_84 DECIMAL(34, 24), float_col_85 FLOAT, boolean_col_86 BOOLEAN, char0233_col_87 CHAR(233)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@table_1_n0 -POSTHOOK: query: CREATE TABLE table_1_n0 (boolean_col_1 BOOLEAN, float_col_2 FLOAT, bigint_col_3 BIGINT, varchar0111_col_4 VARCHAR(111), bigint_col_5 BIGINT, float_col_6 FLOAT, boolean_col_7 BOOLEAN, decimal0101_col_8 DECIMAL(1, 1), decimal0904_col_9 DECIMAL(9, 4), char0112_col_10 CHAR(112), double_col_11 DOUBLE, boolean_col_12 BOOLEAN, double_col_13 DOUBLE, varchar0142_col_14 VARCHAR(142), timestamp_col_15 TIMESTAMP, decimal0502_col_16 DECIMAL(5, 2), smallint_col_25 SMALLINT, decimal3222_col_18 DECIMAL(32, 22), boolean_col_19 BOOLEAN, decimal2012_col_20 DECIMAL(20, 12), char0204_col_21 CHAR(204), double_col_61 DOUBLE, timestamp_col_23 TIMESTAMP, int_col_24 INT, float_col_25 FLOAT, smallint_col_26 SMALLINT, double_col_27 DOUBLE, char0180_col_28 CHAR(180), decimal1503_col_29 DECIMAL(15, 3), timestamp_col_30 TIMESTAMP, smallint_col_31 SMALLINT, decimal2020_col_32 DECIMAL(20, 20), timestamp_col_33 TIMESTAMP, boolean_col_34 BOOLEAN, decimal3025_col_35 DECIMAL(30, 25), decimal3117_col_36 DECIMAL(31, 17), timestamp_col_37 TIMESTAMP, varchar0146_col_38 VARCHAR(146), boolean_col_39 BOOLEAN, double_col_40 DOUBLE, float_col_41 FLOAT, timestamp_col_42 TIMESTAMP, double_col_43 DOUBLE, boolean_col_44 BOOLEAN, timestamp_col_45 TIMESTAMP, tinyint_col_8 TINYINT, int_col_47 INT, decimal0401_col_48 DECIMAL(4, 1), varchar0064_col_49 VARCHAR(64), string_col_50 STRING, double_col_51 DOUBLE, string_col_52 STRING, boolean_col_53 BOOLEAN, int_col_54 INT, boolean_col_55 BOOLEAN, string_col_56 STRING, double_col_57 DOUBLE, varchar0131_col_58 VARCHAR(131), boolean_col_59 BOOLEAN, bigint_col_22 BIGINT, char0184_col_61 CHAR(184), varchar0173_col_62 VARCHAR(173), timestamp_col_63 TIMESTAMP, decimal1709_col_26 DECIMAL(20, 5), timestamp_col_65 TIMESTAMP, timestamp_col_66 TIMESTAMP, timestamp_col_67 TIMESTAMP, boolean_col_68 BOOLEAN, decimal1208_col_20 DECIMAL(33, 11), decimal1605_col_70 DECIMAL(16, 5), varchar0010_col_71 VARCHAR(10), tinyint_col_72 TINYINT, timestamp_col_10 TIMESTAMP, decimal2714_col_74 DECIMAL(27, 14), double_col_75 DOUBLE, boolean_col_76 BOOLEAN, double_col_77 DOUBLE, string_col_78 STRING, boolean_col_79 BOOLEAN, boolean_col_80 BOOLEAN, decimal0803_col_81 DECIMAL(8, 3), decimal1303_col_82 DECIMAL(13, 3), tinyint_col_83 TINYINT, decimal3424_col_84 DECIMAL(34, 24), float_col_85 FLOAT, boolean_col_86 BOOLEAN, char0233_col_87 CHAR(233)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@table_1_n0 -PREHOOK: query: CREATE TABLE table_18_n0 (timestamp_col_1 TIMESTAMP, double_col_2 DOUBLE, boolean_col_3 BOOLEAN, timestamp_col_4 TIMESTAMP, decimal2103_col_5 DECIMAL(21, 3), char0221_col_6 CHAR(221), tinyint_col_7 TINYINT, float_col_8 FLOAT, int_col_2 INT, timestamp_col_10 TIMESTAMP, char0228_col_11 CHAR(228), timestamp_col_12 TIMESTAMP, double_col_13 DOUBLE, tinyint_col_6 TINYINT, tinyint_col_33 TINYINT, smallint_col_38 SMALLINT, boolean_col_17 BOOLEAN, double_col_18 DOUBLE, boolean_col_19 BOOLEAN, bigint_col_20 BIGINT, decimal0504_col_37 DECIMAL(37, 34), boolean_col_22 BOOLEAN, double_col_23 DOUBLE, timestamp_col_24 TIMESTAMP, varchar0076_col_25 VARCHAR(76), timestamp_col_18 TIMESTAMP, boolean_col_27 BOOLEAN, decimal1611_col_22 DECIMAL(37, 5), boolean_col_29 BOOLEAN) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@table_18_n0 -POSTHOOK: query: CREATE TABLE table_18_n0 (timestamp_col_1 TIMESTAMP, double_col_2 DOUBLE, boolean_col_3 BOOLEAN, timestamp_col_4 TIMESTAMP, decimal2103_col_5 DECIMAL(21, 3), char0221_col_6 CHAR(221), tinyint_col_7 TINYINT, float_col_8 FLOAT, int_col_2 INT, timestamp_col_10 TIMESTAMP, char0228_col_11 CHAR(228), timestamp_col_12 TIMESTAMP, double_col_13 DOUBLE, tinyint_col_6 TINYINT, tinyint_col_33 TINYINT, smallint_col_38 SMALLINT, boolean_col_17 BOOLEAN, double_col_18 DOUBLE, boolean_col_19 BOOLEAN, bigint_col_20 BIGINT, decimal0504_col_37 DECIMAL(37, 34), boolean_col_22 BOOLEAN, double_col_23 DOUBLE, timestamp_col_24 TIMESTAMP, varchar0076_col_25 VARCHAR(76), timestamp_col_18 TIMESTAMP, boolean_col_27 BOOLEAN, decimal1611_col_22 DECIMAL(37, 5), boolean_col_29 BOOLEAN) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@table_18_n0 -PREHOOK: query: explain -SELECT -COALESCE(498, LEAD(COALESCE(-973, -684, 515)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25), FLOOR(t1.double_col_61) DESC), 524) AS int_col, -(t2.int_col_2) + (t1.smallint_col_25) AS int_col_1, -FLOOR(t1.double_col_61) AS float_col, -COALESCE(SUM(COALESCE(62, -380, -435)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25) DESC, FLOOR(t1.double_col_61) DESC ROWS BETWEEN UNBOUNDED PRECEDING AND 48 FOLLOWING), 704) AS int_col_2 -FROM table_1_n0 t1 -INNER JOIN table_18_n0 t2 ON (((t2.tinyint_col_6) = (t1.bigint_col_22)) AND ((t2.decimal0504_col_37) = (t1.decimal1709_col_26))) AND ((t2.tinyint_col_33) = (t1.tinyint_col_8)) -WHERE -(t2.smallint_col_38) IN (SELECT -COALESCE(-92, -994) AS int_col -FROM table_1_n0 tt1 -INNER JOIN table_18_n0 tt2 ON (tt2.decimal1611_col_22) = (tt1.decimal1208_col_20) -WHERE -(t1.timestamp_col_10) = (tt2.timestamp_col_18)) -PREHOOK: type: QUERY -PREHOOK: Input: default@table_18_n0 -PREHOOK: Input: default@table_1_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain -SELECT -COALESCE(498, LEAD(COALESCE(-973, -684, 515)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25), FLOOR(t1.double_col_61) DESC), 524) AS int_col, -(t2.int_col_2) + (t1.smallint_col_25) AS int_col_1, -FLOOR(t1.double_col_61) AS float_col, -COALESCE(SUM(COALESCE(62, -380, -435)) OVER (PARTITION BY (t2.int_col_2 + t1.smallint_col_25) ORDER BY (t2.int_col_2 + t1.smallint_col_25) DESC, FLOOR(t1.double_col_61) DESC ROWS BETWEEN UNBOUNDED PRECEDING AND 48 FOLLOWING), 704) AS int_col_2 -FROM table_1_n0 t1 -INNER JOIN table_18_n0 t2 ON (((t2.tinyint_col_6) = (t1.bigint_col_22)) AND ((t2.decimal0504_col_37) = (t1.decimal1709_col_26))) AND ((t2.tinyint_col_33) = (t1.tinyint_col_8)) -WHERE -(t2.smallint_col_38) IN (SELECT -COALESCE(-92, -994) AS int_col -FROM table_1_n0 tt1 -INNER JOIN table_18_n0 tt2 ON (tt2.decimal1611_col_22) = (tt1.decimal1208_col_20) -WHERE -(t1.timestamp_col_10) = (tt2.timestamp_col_18)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@table_18_n0 -POSTHOOK: Input: default@table_1_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-6 - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-6 is a root stage - Stage-0 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: (bigint_col_22 is not null and decimal1709_col_26 is not null and tinyint_col_8 is not null and timestamp_col_10 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (bigint_col_22 is not null and decimal1709_col_26 is not null and tinyint_col_8 is not null and timestamp_col_10 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) - Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE - value expressions: smallint_col_25 (type: smallint), double_col_61 (type: double), timestamp_col_10 (type: timestamp) - TableScan - alias: t2 - filterExpr: (UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null and tinyint_col_33 is not null and UDFToInteger(smallint_col_38) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToLong(tinyint_col_6) is not null and decimal0504_col_37 is not null and tinyint_col_33 is not null and UDFToInteger(smallint_col_38) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) - null sort order: zzz - sort order: +++ - Map-reduce partition columns: UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) - Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: NONE - value expressions: int_col_2 (type: int), smallint_col_38 (type: smallint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 bigint_col_22 (type: bigint), decimal1709_col_26 (type: decimal(38,23)), tinyint_col_8 (type: tinyint) - 1 UDFToLong(tinyint_col_6) (type: bigint), decimal0504_col_37 (type: decimal(38,23)), tinyint_col_33 (type: tinyint) - outputColumnNames: _col16, _col21, _col72, _col98, _col105 - Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: UDFToInteger(_col105) (type: int), _col72 (type: timestamp) - null sort order: zz - sort order: ++ - Map-reduce partition columns: UDFToInteger(_col105) (type: int), _col72 (type: timestamp) - Statistics: Num rows: 1 Data size: 193 Basic stats: COMPLETE Column stats: NONE - value expressions: _col16 (type: smallint), _col21 (type: double), _col98 (type: int) - TableScan - Reduce Output Operator - key expressions: -92 (type: int), _col1 (type: timestamp) - null sort order: zz - sort order: ++ - Map-reduce partition columns: -92 (type: int), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 UDFToInteger(_col105) (type: int), _col72 (type: timestamp) - 1 _col0 (type: int), _col1 (type: timestamp) - outputColumnNames: _col16, _col21, _col98 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: (_col98 + _col16) (type: int), floor(_col21) (type: bigint) - null sort order: zz - sort order: +- - Map-reduce partition columns: (_col98 + _col16) (type: int) - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col16 (type: smallint), _col21 (type: double), _col98 (type: int) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col16 (type: smallint), VALUE._col21 (type: double), VALUE._col98 (type: int) - outputColumnNames: _col16, _col21, _col98 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col16: smallint, _col21: double, _col98: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (_col98 + _col16) ASC NULLS LAST, floor(_col21) DESC NULLS LAST - partition by: (_col98 + _col16) - raw input shape: - window functions: - window function definition - alias: LEAD_window_0 - arguments: COALESCE(-973,-684,515) - name: LEAD - window function: GenericUDAFLeadEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: LEAD_window_0 (type: int), _col16 (type: smallint), _col21 (type: double), _col98 (type: int) - outputColumnNames: LEAD_window_0, _col16, _col21, _col98 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: (_col98 + _col16) (type: int), floor(_col21) (type: bigint) - null sort order: zz - sort order: -- - Map-reduce partition columns: (_col98 + _col16) (type: int) - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - value expressions: LEAD_window_0 (type: int), _col16 (type: smallint), _col21 (type: double), _col98 (type: int) - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col17 (type: smallint), VALUE._col22 (type: double), VALUE._col99 (type: int) - outputColumnNames: _col0, _col17, _col22, _col99 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col17: smallint, _col22: double, _col99: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (_col99 + _col17) DESC NULLS LAST, floor(_col22) DESC NULLS LAST - partition by: (_col99 + _col17) - raw input shape: - window functions: - window function definition - alias: SUM_window_1 - arguments: COALESCE(62,-380,-435) - name: SUM - window function: GenericUDAFSumLong - window frame: ROWS PRECEDING(MAX)~FOLLOWING(48) - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: COALESCE(498,_col0,524) (type: int), (_col99 + _col17) (type: int), floor(_col22) (type: bigint), COALESCE(SUM_window_1,704) (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 212 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: tt1 - filterExpr: decimal1208_col_20 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: decimal1208_col_20 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: decimal1208_col_20 (type: decimal(38,6)) - null sort order: z - sort order: + - Map-reduce partition columns: decimal1208_col_20 (type: decimal(38,6)) - Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: tt2 - filterExpr: (decimal1611_col_22 is not null and timestamp_col_18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (decimal1611_col_22 is not null and timestamp_col_18 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: decimal1611_col_22 (type: decimal(38,6)) - null sort order: z - sort order: + - Map-reduce partition columns: decimal1611_col_22 (type: decimal(38,6)) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - value expressions: timestamp_col_18 (type: timestamp) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 decimal1208_col_20 (type: decimal(38,6)) - 1 decimal1611_col_22 (type: decimal(38,6)) - outputColumnNames: _col115 - Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col115 (type: timestamp) - outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: -92 (type: int), _col1 (type: timestamp) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 123 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/semijoin3.q.out ql/src/test/results/clientpositive/semijoin3.q.out deleted file mode 100644 index 3fff13122c..0000000000 --- ql/src/test/results/clientpositive/semijoin3.q.out +++ /dev/null @@ -1,173 +0,0 @@ -PREHOOK: query: create table t1_n59 as select cast(key as int) key, value from src -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@t1_n59 -POSTHOOK: query: create table t1_n59 as select cast(key as int) key, value from src -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t1_n59 -POSTHOOK: Lineage: t1_n59.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: t1_n59.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: create table t2_n37 as select cast(key as int) key, value from src -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@t2_n37 -POSTHOOK: query: create table t2_n37 as select cast(key as int) key, value from src -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t2_n37 -POSTHOOK: Lineage: t2_n37.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: t2_n37.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain -select count(1) -from - (select key - from t1_n59 - where key = 0) t1_n59 -left semi join - (select key - from t2_n37 - where key = 0) t2_n37 -on 1 = 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n59 -PREHOOK: Input: default@t2_n37 -#### A masked pattern was here #### -POSTHOOK: query: explain -select count(1) -from - (select key - from t1_n59 - where key = 0) t1_n59 -left semi join - (select key - from t2_n37 - where key = 0) t2_n37 -on 1 = 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n59 -POSTHOOK: Input: default@t2_n37 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n59 - filterExpr: (key = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 0) (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: t2_n37 - filterExpr: (key = 0) (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 0) (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 1 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 1 (type: int) - 1 1 (type: int) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(1) -from - (select key - from t1_n59 - where key = 0) t1_n59 -left semi join - (select key - from t2_n37 - where key = 0) t2_n37 -on 1 = 1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n59 -PREHOOK: Input: default@t2_n37 -#### A masked pattern was here #### -POSTHOOK: query: select count(1) -from - (select key - from t1_n59 - where key = 0) t1_n59 -left semi join - (select key - from t2_n37 - where key = 0) t2_n37 -on 1 = 1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n59 -POSTHOOK: Input: default@t2_n37 -#### A masked pattern was here #### -3 diff --git ql/src/test/results/clientpositive/semijoin4.q.out ql/src/test/results/clientpositive/semijoin4.q.out deleted file mode 100644 index e3f625c512..0000000000 --- ql/src/test/results/clientpositive/semijoin4.q.out +++ /dev/null @@ -1,246 +0,0 @@ -PREHOOK: query: CREATE TABLE table_1 (int_col_1 INT, decimal3003_col_2 DECIMAL(30, 3), timestamp_col_3 TIMESTAMP, decimal0101_col_4 DECIMAL(1, 1), double_col_5 DOUBLE, boolean_col_6 BOOLEAN, timestamp_col_7 TIMESTAMP, varchar0098_col_8 VARCHAR(98), int_col_9 INT, timestamp_col_10 TIMESTAMP, decimal0903_col_11 DECIMAL(9, 3), int_col_12 INT, bigint_col_13 BIGINT, boolean_col_14 BOOLEAN, char0254_col_15 CHAR(254), boolean_col_16 BOOLEAN, smallint_col_17 SMALLINT, float_col_18 FLOAT, decimal2608_col_19 DECIMAL(26, 8), varchar0216_col_20 VARCHAR(216), string_col_21 STRING, timestamp_col_22 TIMESTAMP, double_col_23 DOUBLE, smallint_col_24 SMALLINT, float_col_25 FLOAT, decimal2016_col_26 DECIMAL(20, 16), string_col_27 STRING, decimal0202_col_28 DECIMAL(2, 2), boolean_col_29 BOOLEAN, decimal2020_col_30 DECIMAL(20, 20), float_col_31 FLOAT, boolean_col_32 BOOLEAN, varchar0148_col_33 VARCHAR(148), decimal2121_col_34 DECIMAL(21, 21), timestamp_col_35 TIMESTAMP, float_col_36 FLOAT, float_col_37 FLOAT, string_col_38 STRING, decimal3420_col_39 DECIMAL(34, 20), smallint_col_40 SMALLINT, decimal1408_col_41 DECIMAL(14, 8), string_col_42 STRING, decimal0902_col_43 DECIMAL(9, 2), varchar0204_col_44 VARCHAR(204), float_col_45 FLOAT, tinyint_col_46 TINYINT, double_col_47 DOUBLE, timestamp_col_48 TIMESTAMP, double_col_49 DOUBLE, timestamp_col_50 TIMESTAMP, decimal0704_col_51 DECIMAL(7, 4), int_col_52 INT, double_col_53 DOUBLE, int_col_54 INT, timestamp_col_55 TIMESTAMP, decimal0505_col_56 DECIMAL(5, 5), char0155_col_57 CHAR(155), double_col_58 DOUBLE, timestamp_col_59 TIMESTAMP, double_col_60 DOUBLE, float_col_61 FLOAT, char0249_col_62 CHAR(249), float_col_63 FLOAT, smallint_col_64 SMALLINT, decimal1309_col_65 DECIMAL(13, 9), timestamp_col_66 TIMESTAMP, boolean_col_67 BOOLEAN, tinyint_col_68 TINYINT, tinyint_col_69 TINYINT, double_col_70 DOUBLE, bigint_col_71 BIGINT, boolean_col_72 BOOLEAN, float_col_73 FLOAT, char0222_col_74 CHAR(222), boolean_col_75 BOOLEAN, string_col_76 STRING, decimal2612_col_77 DECIMAL(26, 12), bigint_col_78 BIGINT, char0128_col_79 CHAR(128), tinyint_col_80 TINYINT, boolean_col_81 BOOLEAN, int_col_82 INT, boolean_col_83 BOOLEAN, decimal2622_col_84 DECIMAL(26, 22), boolean_col_85 BOOLEAN, boolean_col_86 BOOLEAN, decimal0907_col_87 DECIMAL(9, 7)) -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@table_1 -POSTHOOK: query: CREATE TABLE table_1 (int_col_1 INT, decimal3003_col_2 DECIMAL(30, 3), timestamp_col_3 TIMESTAMP, decimal0101_col_4 DECIMAL(1, 1), double_col_5 DOUBLE, boolean_col_6 BOOLEAN, timestamp_col_7 TIMESTAMP, varchar0098_col_8 VARCHAR(98), int_col_9 INT, timestamp_col_10 TIMESTAMP, decimal0903_col_11 DECIMAL(9, 3), int_col_12 INT, bigint_col_13 BIGINT, boolean_col_14 BOOLEAN, char0254_col_15 CHAR(254), boolean_col_16 BOOLEAN, smallint_col_17 SMALLINT, float_col_18 FLOAT, decimal2608_col_19 DECIMAL(26, 8), varchar0216_col_20 VARCHAR(216), string_col_21 STRING, timestamp_col_22 TIMESTAMP, double_col_23 DOUBLE, smallint_col_24 SMALLINT, float_col_25 FLOAT, decimal2016_col_26 DECIMAL(20, 16), string_col_27 STRING, decimal0202_col_28 DECIMAL(2, 2), boolean_col_29 BOOLEAN, decimal2020_col_30 DECIMAL(20, 20), float_col_31 FLOAT, boolean_col_32 BOOLEAN, varchar0148_col_33 VARCHAR(148), decimal2121_col_34 DECIMAL(21, 21), timestamp_col_35 TIMESTAMP, float_col_36 FLOAT, float_col_37 FLOAT, string_col_38 STRING, decimal3420_col_39 DECIMAL(34, 20), smallint_col_40 SMALLINT, decimal1408_col_41 DECIMAL(14, 8), string_col_42 STRING, decimal0902_col_43 DECIMAL(9, 2), varchar0204_col_44 VARCHAR(204), float_col_45 FLOAT, tinyint_col_46 TINYINT, double_col_47 DOUBLE, timestamp_col_48 TIMESTAMP, double_col_49 DOUBLE, timestamp_col_50 TIMESTAMP, decimal0704_col_51 DECIMAL(7, 4), int_col_52 INT, double_col_53 DOUBLE, int_col_54 INT, timestamp_col_55 TIMESTAMP, decimal0505_col_56 DECIMAL(5, 5), char0155_col_57 CHAR(155), double_col_58 DOUBLE, timestamp_col_59 TIMESTAMP, double_col_60 DOUBLE, float_col_61 FLOAT, char0249_col_62 CHAR(249), float_col_63 FLOAT, smallint_col_64 SMALLINT, decimal1309_col_65 DECIMAL(13, 9), timestamp_col_66 TIMESTAMP, boolean_col_67 BOOLEAN, tinyint_col_68 TINYINT, tinyint_col_69 TINYINT, double_col_70 DOUBLE, bigint_col_71 BIGINT, boolean_col_72 BOOLEAN, float_col_73 FLOAT, char0222_col_74 CHAR(222), boolean_col_75 BOOLEAN, string_col_76 STRING, decimal2612_col_77 DECIMAL(26, 12), bigint_col_78 BIGINT, char0128_col_79 CHAR(128), tinyint_col_80 TINYINT, boolean_col_81 BOOLEAN, int_col_82 INT, boolean_col_83 BOOLEAN, decimal2622_col_84 DECIMAL(26, 22), boolean_col_85 BOOLEAN, boolean_col_86 BOOLEAN, decimal0907_col_87 DECIMAL(9, 7)) -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@table_1 -PREHOOK: query: CREATE TABLE table_18 (float_col_1 FLOAT, double_col_2 DOUBLE, decimal2518_col_3 DECIMAL(25, 18), boolean_col_4 BOOLEAN, bigint_col_5 BIGINT, boolean_col_6 BOOLEAN, boolean_col_7 BOOLEAN, char0035_col_8 CHAR(35), decimal2709_col_9 DECIMAL(27, 9), timestamp_col_10 TIMESTAMP, bigint_col_11 BIGINT, decimal3604_col_12 DECIMAL(36, 4), string_col_13 STRING, timestamp_col_14 TIMESTAMP, timestamp_col_15 TIMESTAMP, decimal1911_col_16 DECIMAL(19, 11), boolean_col_17 BOOLEAN, tinyint_col_18 TINYINT, timestamp_col_19 TIMESTAMP, timestamp_col_20 TIMESTAMP, tinyint_col_21 TINYINT, float_col_22 FLOAT, timestamp_col_23 TIMESTAMP) -STORED AS orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@table_18 -POSTHOOK: query: CREATE TABLE table_18 (float_col_1 FLOAT, double_col_2 DOUBLE, decimal2518_col_3 DECIMAL(25, 18), boolean_col_4 BOOLEAN, bigint_col_5 BIGINT, boolean_col_6 BOOLEAN, boolean_col_7 BOOLEAN, char0035_col_8 CHAR(35), decimal2709_col_9 DECIMAL(27, 9), timestamp_col_10 TIMESTAMP, bigint_col_11 BIGINT, decimal3604_col_12 DECIMAL(36, 4), string_col_13 STRING, timestamp_col_14 TIMESTAMP, timestamp_col_15 TIMESTAMP, decimal1911_col_16 DECIMAL(19, 11), boolean_col_17 BOOLEAN, tinyint_col_18 TINYINT, timestamp_col_19 TIMESTAMP, timestamp_col_20 TIMESTAMP, tinyint_col_21 TINYINT, float_col_22 FLOAT, timestamp_col_23 TIMESTAMP) -STORED AS orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@table_18 -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: explain -SELECT - COALESCE(498, - LEAD(COALESCE(-973, -684, 515)) OVER ( - PARTITION BY (t2.tinyint_col_21 + t1.smallint_col_24) - ORDER BY (t2.tinyint_col_21 + t1.smallint_col_24), - FLOOR(t1.double_col_60) DESC), - 524) AS int_col -FROM table_1 t1 INNER JOIN table_18 t2 -ON (((t2.tinyint_col_18) = (t1.bigint_col_13)) - AND ((t2.decimal2709_col_9) = (t1.decimal1309_col_65))) - AND ((t2.tinyint_col_21) = (t1.tinyint_col_46)) -WHERE (t2.tinyint_col_21) IN ( - SELECT COALESCE(-92, -994) AS int_col_3 - FROM table_1 tt1 INNER JOIN table_18 tt2 - ON (tt2.decimal1911_col_16) = (tt1.decimal1309_col_65) - WHERE (tt1.timestamp_col_66) = (tt2.timestamp_col_19)) -PREHOOK: type: QUERY -PREHOOK: Input: default@table_1 -PREHOOK: Input: default@table_18 -#### A masked pattern was here #### -POSTHOOK: query: explain -SELECT - COALESCE(498, - LEAD(COALESCE(-973, -684, 515)) OVER ( - PARTITION BY (t2.tinyint_col_21 + t1.smallint_col_24) - ORDER BY (t2.tinyint_col_21 + t1.smallint_col_24), - FLOOR(t1.double_col_60) DESC), - 524) AS int_col -FROM table_1 t1 INNER JOIN table_18 t2 -ON (((t2.tinyint_col_18) = (t1.bigint_col_13)) - AND ((t2.decimal2709_col_9) = (t1.decimal1309_col_65))) - AND ((t2.tinyint_col_21) = (t1.tinyint_col_46)) -WHERE (t2.tinyint_col_21) IN ( - SELECT COALESCE(-92, -994) AS int_col_3 - FROM table_1 tt1 INNER JOIN table_18 tt2 - ON (tt2.decimal1911_col_16) = (tt1.decimal1309_col_65) - WHERE (tt1.timestamp_col_66) = (tt2.timestamp_col_19)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@table_1 -POSTHOOK: Input: default@table_18 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-4 is a root stage - Stage-5 depends on stages: Stage-4 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((tinyint_col_46 = -92Y) and bigint_col_13 is not null and decimal1309_col_65 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((tinyint_col_46 = -92Y) and bigint_col_13 is not null and decimal1309_col_65 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: bigint_col_13 (type: bigint), decimal1309_col_65 (type: decimal(13,9)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: bigint), _col1 (type: decimal(27,9)) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: bigint), _col1 (type: decimal(27,9)) - Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: t2 - filterExpr: ((tinyint_col_21 = -92Y) and UDFToLong(tinyint_col_18) is not null and decimal2709_col_9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((tinyint_col_21 = -92Y) and UDFToLong(tinyint_col_18) is not null and decimal2709_col_9 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: decimal2709_col_9 (type: decimal(27,9)), UDFToLong(tinyint_col_18) (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: bigint), _col0 (type: decimal(27,9)) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: bigint), _col0 (type: decimal(27,9)) - Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: bigint), _col1 (type: decimal(27,9)) - 1 _col1 (type: bigint), _col0 (type: decimal(27,9)) - Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - Statistics: Num rows: 1 Data size: 304 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 498 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 304 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 304 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: tt1 - filterExpr: (decimal1309_col_65 is not null and timestamp_col_66 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (decimal1309_col_65 is not null and timestamp_col_66 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: decimal1309_col_65 (type: decimal(13,9)), timestamp_col_66 (type: timestamp) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: decimal(19,11)), _col1 (type: timestamp) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(19,11)), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: tt2 - filterExpr: (decimal1911_col_16 is not null and timestamp_col_19 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (decimal1911_col_16 is not null and timestamp_col_19 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: decimal1911_col_16 (type: decimal(19,11)), timestamp_col_19 (type: timestamp) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: decimal(19,11)), _col1 (type: timestamp) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(19,11)), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 152 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: decimal(19,11)), _col1 (type: timestamp) - 1 _col0 (type: decimal(19,11)), _col1 (type: timestamp) - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: true (type: boolean) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: boolean) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: boolean) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 167 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/set_processor_namespaces.q.out ql/src/test/results/clientpositive/set_processor_namespaces.q.out deleted file mode 100644 index 7952d7c355..0000000000 --- ql/src/test/results/clientpositive/set_processor_namespaces.q.out +++ /dev/null @@ -1,61 +0,0 @@ -zzz=5 -system:xxx=5 -system:yyy=5 -go=5 -raw=${hiveconf:zzz} -PREHOOK: query: EXPLAIN SELECT * FROM src where key=5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src where key=5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) = 5.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) = 5.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM src where key=5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM src where key=5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -5 val_5 -5 val_5 -5 val_5 -c=1 -x=1 -x=2 diff --git ql/src/test/results/clientpositive/set_variable_sub.q.out ql/src/test/results/clientpositive/set_variable_sub.q.out deleted file mode 100644 index 10604623c2..0000000000 --- ql/src/test/results/clientpositive/set_variable_sub.q.out +++ /dev/null @@ -1,130 +0,0 @@ -PREHOOK: query: EXPLAIN SELECT * FROM src where key="value1" -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src where key="value1" -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = 'value1') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 'value1') (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'value1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN SELECT * FROM src where key="value1" -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src where key="value1" -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = 'value1') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 'value1') (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'value1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 362 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: EXPLAIN SELECT * FROM src where key="1" -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN SELECT * FROM src where key="1" -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = '1') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = '1') (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: '1' (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 352 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -hivevar:a=1 -hivevar:b=a -hivevar:c=1 -hivevar:key1=value1 diff --git ql/src/test/results/clientpositive/setop_subq.q.out ql/src/test/results/clientpositive/setop_subq.q.out deleted file mode 100644 index 16def08266..0000000000 --- ql/src/test/results/clientpositive/setop_subq.q.out +++ /dev/null @@ -1,627 +0,0 @@ -PREHOOK: query: explain select key from ((select key from src) union (select key from src))subq -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select key from ((select key from src) union (select key from src))subq -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select key from ((select key from src) intersect (select key from src))subq -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select key from ((select key from src) intersect (select key from src))subq -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - TableScan - Union - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select key from ((select key from src) intersect select key from src)subq -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select key from ((select key from src) intersect select key from src)subq -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - TableScan - Union - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select key from (select key from src intersect (select key from src))subq -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select key from (select key from src intersect (select key from src))subq -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - TableScan - Union - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col1 = 2L) (type: boolean) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select a.key, b.value from ( (select key from src)a join (select value from src)b on a.key=b.value) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select a.key, b.value from ( (select key from src)a join (select value from src)b on a.key=b.value) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out deleted file mode 100644 index 537085f80b..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out +++ /dev/null @@ -1,640 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n67(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n67 -POSTHOOK: query: CREATE TABLE T1_n67(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n67 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n67 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n67 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n67 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n67 -PREHOOK: query: CREATE TABLE T2_n40(key STRING, val STRING) -SKEWED BY (key) ON ((3)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n40 -POSTHOOK: query: CREATE TABLE T2_n40(key STRING, val STRING) -SKEWED BY (key) ON ((3)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n40 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n40 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n40 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n40 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n40 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -NULL NULL 4 14 -NULL NULL 5 15 -PREHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(1) FROM T1_n67 a JOIN T2_n40 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -6 -PREHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n67 -PREHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(1) FROM T1_n67 a RIGHT OUTER JOIN T2_n40 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n67 -POSTHOOK: Input: default@t2_n40 -#### A masked pattern was here #### -8 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out deleted file mode 100644 index e6bd67a78b..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out +++ /dev/null @@ -1,672 +0,0 @@ -PREHOOK: query: CREATE TABLE tmpT1_n0(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmpT1_n0 -POSTHOOK: query: CREATE TABLE tmpT1_n0(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmpT1_n0 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1_n0 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@tmpt1_n0 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE tmpT1_n0 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@tmpt1_n0 -PREHOOK: query: CREATE TABLE T1_n151(key INT, val STRING) SKEWED BY (key) ON ((2)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n151 -POSTHOOK: query: CREATE TABLE T1_n151(key INT, val STRING) SKEWED BY (key) ON ((2)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n151 -PREHOOK: query: INSERT OVERWRITE TABLE T1_n151 SELECT key, val FROM tmpT1_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmpt1_n0 -PREHOOK: Output: default@t1_n151 -POSTHOOK: query: INSERT OVERWRITE TABLE T1_n151 SELECT key, val FROM tmpT1_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmpt1_n0 -POSTHOOK: Output: default@t1_n151 -POSTHOOK: Lineage: t1_n151.key EXPRESSION [(tmpt1_n0)tmpt1_n0.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: t1_n151.val SIMPLE [(tmpt1_n0)tmpt1_n0.FieldSchema(name:val, type:string, comment:null), ] -PREHOOK: query: CREATE TABLE tmpT2_n0(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmpT2_n0 -POSTHOOK: query: CREATE TABLE tmpT2_n0(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmpT2_n0 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2_n0 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@tmpt2_n0 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE tmpT2_n0 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@tmpt2_n0 -PREHOOK: query: CREATE TABLE T2_n88(key INT, val STRING) SKEWED BY (key) ON ((3)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n88 -POSTHOOK: query: CREATE TABLE T2_n88(key INT, val STRING) SKEWED BY (key) ON ((3)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n88 -PREHOOK: query: INSERT OVERWRITE TABLE T2_n88 SELECT key, val FROM tmpT2_n0 -PREHOOK: type: QUERY -PREHOOK: Input: default@tmpt2_n0 -PREHOOK: Output: default@t2_n88 -POSTHOOK: query: INSERT OVERWRITE TABLE T2_n88 SELECT key, val FROM tmpT2_n0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tmpt2_n0 -POSTHOOK: Output: default@t2_n88 -POSTHOOK: Lineage: t2_n88.key EXPRESSION [(tmpt2_n0)tmpt2_n0.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: t2_n88.val SIMPLE [(tmpt2_n0)tmpt2_n0.FieldSchema(name:val, type:string, comment:null), ] -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 1080 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -NULL NULL 4 14 -NULL NULL 5 15 -PREHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - TableScan - alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(1) FROM T1_n151 a JOIN T2_n88 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -6 -PREHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key = 2) or (key = 3)) (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - TableScan - alias: b - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (not ((key = 2) or (key = 3))) (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Union - Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n151 -PREHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -POSTHOOK: query: SELECT count(1) FROM T1_n151 a RIGHT OUTER JOIN T2_n88 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n151 -POSTHOOK: Input: default@t2_n88 -#### A masked pattern was here #### -8 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out deleted file mode 100644 index 5fc405ba9a..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin11.q.out +++ /dev/null @@ -1,181 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n31(key STRING, val STRING) -CLUSTERED BY (key) INTO 4 BUCKETS -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n31 -POSTHOOK: query: CREATE TABLE T1_n31(key STRING, val STRING) -CLUSTERED BY (key) INTO 4 BUCKETS -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n31 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/bucket_files/000000_0' INTO TABLE T1_n31 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n31 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/bucket_files/000000_0' INTO TABLE T1_n31 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n31 -PREHOOK: query: CREATE TABLE T2_n21(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n21 -POSTHOOK: query: CREATE TABLE T2_n21(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n21 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n21 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n21 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n21 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n21 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n31 -PREHOOK: Input: default@t2_n21 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n31 -POSTHOOK: Input: default@t2_n21 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n31 -PREHOOK: Input: default@t2_n21 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n31 a JOIN T2_n21 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n31 -POSTHOOK: Input: default@t2_n21 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out deleted file mode 100644 index 0d770d9ab8..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin2.q.out +++ /dev/null @@ -1,358 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n25(key STRING, val STRING) -SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n25 -POSTHOOK: query: CREATE TABLE T1_n25(key STRING, val STRING) -SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n25 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n25 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n25 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n25 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n25 -PREHOOK: query: CREATE TABLE T2_n16(key STRING, val STRING) -SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n16 -POSTHOOK: query: CREATE TABLE T2_n16(key STRING, val STRING) -SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n16 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n16 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n16 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n16 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n16 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n25 -PREHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n25 -POSTHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n25 -PREHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n25 a JOIN T2_n16 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n25 -POSTHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n25 -PREHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n25 -POSTHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-4 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key = '2') or (key = '8')) or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key = '2') or (key = '8')) or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Full Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n25 -PREHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n25 a FULL OUTER JOIN T2_n16 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n25 -POSTHOOK: Input: default@t2_n16 -#### A masked pattern was here #### -1 11 NULL NULL -2 12 2 22 -3 13 3 13 -7 17 NULL NULL -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -NULL NULL 4 14 -NULL NULL 5 15 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out deleted file mode 100644 index 42c9319940..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin3.q.out +++ /dev/null @@ -1,181 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n155(key STRING, val STRING) -SKEWED BY (key, val) ON ((2, 12), (8, 18)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n155 -POSTHOOK: query: CREATE TABLE T1_n155(key STRING, val STRING) -SKEWED BY (key, val) ON ((2, 12), (8, 18)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n155 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n155 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n155 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n155 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n155 -PREHOOK: query: CREATE TABLE T2_n91(key STRING, val STRING) -SKEWED BY (key, val) ON ((3, 13), (8, 18)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n91 -POSTHOOK: query: CREATE TABLE T2_n91(key STRING, val STRING) -SKEWED BY (key, val) ON ((3, 13), (8, 18)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n91 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n91 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n91 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n91 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n91 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n155 -PREHOOK: Input: default@t2_n91 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n155 -POSTHOOK: Input: default@t2_n91 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n155 -PREHOOK: Input: default@t2_n91 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n155 a JOIN T2_n91 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n155 -POSTHOOK: Input: default@t2_n91 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out deleted file mode 100644 index 9c8fa2ce73..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin4.q.out +++ /dev/null @@ -1,231 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n124(key STRING, val STRING) -SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n124 -POSTHOOK: query: CREATE TABLE T1_n124(key STRING, val STRING) -SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n124 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n124 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n124 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n124 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n124 -PREHOOK: query: CREATE TABLE T2_n73(key STRING, val STRING) -SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n73 -POSTHOOK: query: CREATE TABLE T2_n73(key STRING, val STRING) -SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n73 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n73 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n73 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n73 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n73 -PREHOOK: query: CREATE TABLE T3_n27(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T3_n27 -POSTHOOK: query: CREATE TABLE T3_n27(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T3_n27 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n27 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t3_n27 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n27 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t3_n27 -PREHOOK: query: EXPLAIN -SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n124 -PREHOOK: Input: default@t2_n73 -PREHOOK: Input: default@t3_n27 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n124 -POSTHOOK: Input: default@t2_n73 -POSTHOOK: Input: default@t3_n27 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-10 is a root stage - Stage-7 depends on stages: Stage-10 - Stage-0 depends on stages: Stage-7 - -STAGE PLANS: - Stage: Stage-10 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - $hdt$_2:c - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_2:c - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key -ORDER BY a.key, b.key, c.key, a.val, b.val, c.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n124 -PREHOOK: Input: default@t2_n73 -PREHOOK: Input: default@t3_n27 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.*, c.* FROM T1_n124 a JOIN T2_n73 b ON a.key = b.key JOIN T3_n27 c on a.key = c.key -ORDER BY a.key, b.key, c.key, a.val, b.val, c.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n124 -POSTHOOK: Input: default@t2_n73 -POSTHOOK: Input: default@t3_n27 -#### A masked pattern was here #### -2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out deleted file mode 100644 index 6796c3b830..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out +++ /dev/null @@ -1,335 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n87(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n87 -POSTHOOK: query: CREATE TABLE T1_n87(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n87 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n87 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n87 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n87 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n87 -PREHOOK: query: CREATE TABLE T2_n54(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n54 -POSTHOOK: query: CREATE TABLE T2_n54(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n54 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n54 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n54 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n54 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n54 -PREHOOK: query: EXPLAIN -select * from -( -select key, val from T1_n87 - union all -select key, val from T1_n87 -) subq1 -join T2_n54 b on subq1.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n87 -PREHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -select * from -( -select key, val from T1_n87 - union all -select key, val from T1_n87 -) subq1 -join T2_n54 b on subq1.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n87 -POSTHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-5 is a root stage - Stage-4 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n87 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: t1_n87 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from -( -select key, val from T1_n87 - union all -select key, val from T1_n87 -) subq1 -join T2_n54 b on subq1.key = b.key -ORDER BY subq1.key, b.key, subq1.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n87 -PREHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -POSTHOOK: query: select * from -( -select key, val from T1_n87 - union all -select key, val from T1_n87 -) subq1 -join T2_n54 b on subq1.key = b.key -ORDER BY subq1.key, b.key, subq1.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n87 -POSTHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -2 12 2 22 -2 12 2 22 -3 13 3 13 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -8 28 8 18 -8 28 8 18 -PREHOOK: query: EXPLAIN -select * from -( -select key, count(1) as cnt from T1_n87 group by key -) subq1 -join T2_n54 b on subq1.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n87 -PREHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -select * from -( -select key, count(1) as cnt from T1_n87 group by key -) subq1 -join T2_n54 b on subq1.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n87 -POSTHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-5 depends on stages: Stage-1 - Stage-4 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n87 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from -( -select key, count(1) as cnt from T1_n87 group by key -) subq1 -join T2_n54 b on subq1.key = b.key -ORDER BY subq1.key, b.key, subq1.cnt, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n87 -PREHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -POSTHOOK: query: select * from -( -select key, count(1) as cnt from T1_n87 group by key -) subq1 -join T2_n54 b on subq1.key = b.key -ORDER BY subq1.key, b.key, subq1.cnt, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n87 -POSTHOOK: Input: default@t2_n54 -#### A masked pattern was here #### -2 1 2 22 -3 1 3 13 -8 2 8 18 -8 2 8 18 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out deleted file mode 100644 index bdebe7e34d..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin6.q.out +++ /dev/null @@ -1,229 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n39(key STRING, value STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n39 -POSTHOOK: query: CREATE TABLE T1_n39(key STRING, value STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n39 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n39 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n39 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n39 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n39 -PREHOOK: query: drop table array_valued_T1_n39 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table array_valued_T1_n39 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table array_valued_T1_n39 (key string, value array) SKEWED BY (key) ON ((8)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@array_valued_T1_n39 -POSTHOOK: query: create table array_valued_T1_n39 (key string, value array) SKEWED BY (key) ON ((8)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@array_valued_T1_n39 -PREHOOK: query: insert overwrite table array_valued_T1_n39 select key, array(value) from T1_n39 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n39 -PREHOOK: Output: default@array_valued_t1_n39 -POSTHOOK: query: insert overwrite table array_valued_T1_n39 select key, array(value) from T1_n39 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n39 -POSTHOOK: Output: default@array_valued_t1_n39 -POSTHOOK: Lineage: array_valued_t1_n39.key SIMPLE [(t1_n39)t1_n39.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: array_valued_t1_n39.value EXPRESSION [(t1_n39)t1_n39.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: explain -select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val -PREHOOK: type: QUERY -PREHOOK: Input: default@array_valued_t1_n39 -PREHOOK: Input: default@t1_n39 -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@array_valued_t1_n39 -POSTHOOK: Input: default@t1_n39 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - i:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - i:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '8')) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: string) - 1 key (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '8'))) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: string) - 1 key (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '8')) (type: boolean) - Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col6 - Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col6 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 13886 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col1 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 6 Data size: 12624 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '8'))) (type: boolean) - Statistics: Num rows: 1 Data size: 2104 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col6 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col6 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: array) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: _col1 (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 7 Data size: 14088 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 14 Data size: 28176 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val -ORDER BY key, val -PREHOOK: type: QUERY -PREHOOK: Input: default@array_valued_t1_n39 -PREHOOK: Input: default@t1_n39 -#### A masked pattern was here #### -POSTHOOK: query: select * from (select a.key as key, b.value as array_val from T1_n39 a join array_valued_T1_n39 b on a.key=b.key) i lateral view explode (array_val) c as val -ORDER BY key, val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@array_valued_t1_n39 -POSTHOOK: Input: default@t1_n39 -#### A masked pattern was here #### -1 ["11"] 11 -2 ["12"] 12 -3 ["13"] 13 -7 ["17"] 17 -8 ["18"] 18 -8 ["18"] 18 -8 ["28"] 28 -8 ["28"] 28 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out deleted file mode 100644 index b62203aeca..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin7.q.out +++ /dev/null @@ -1,347 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n157(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n157 -POSTHOOK: query: CREATE TABLE T1_n157(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n157 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n157 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n157 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n157 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n157 -PREHOOK: query: CREATE TABLE T2_n92(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n92 -POSTHOOK: query: CREATE TABLE T2_n92(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n92 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n92 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n92 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n92 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n92 -PREHOOK: query: EXPLAIN -select * from -( - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key - union all - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key -) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n157 -PREHOOK: Input: default@t2_n92 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -select * from -( - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key - union all - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key -) subq1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n157 -POSTHOOK: Input: default@t2_n92 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-16 is a root stage - Stage-2 depends on stages: Stage-16 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-17 is a root stage - Stage-6 depends on stages: Stage-17 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-16 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0-subquery1:$hdt$_0:a - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0-subquery1:$hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - Union - Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 1616 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-17 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0-subquery2:$hdt$_0:a - Fetch Operator - limit: -1 - subquery2:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0-subquery2:$hdt$_0:a - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - subquery2:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from -( - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key - union all - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key -) subq1 -ORDER BY key, val1, val2 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n157 -PREHOOK: Input: default@t2_n92 -#### A masked pattern was here #### -POSTHOOK: query: select * from -( - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key - union all - select a.key, a.val as val1, b.val as val2 from T1_n157 a join T2_n92 b on a.key = b.key -) subq1 -ORDER BY key, val1, val2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n157 -POSTHOOK: Input: default@t2_n92 -#### A masked pattern was here #### -2 12 22 -2 12 22 -3 13 13 -3 13 13 -8 18 18 -8 18 18 -8 18 18 -8 18 18 -8 28 18 -8 28 18 -8 28 18 -8 28 18 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out deleted file mode 100644 index 131c1848a4..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin8.q.out +++ /dev/null @@ -1,187 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n29(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n29 -POSTHOOK: query: CREATE TABLE T1_n29(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n29 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n29 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n29 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n29 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n29 -PREHOOK: query: CREATE TABLE T2_n20(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n20 -POSTHOOK: query: CREATE TABLE T2_n20(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n20 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n20 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n20 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n20 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n20 -PREHOOK: query: CREATE TABLE T3_n7(key STRING, val STRING) -SKEWED BY (val) ON ((12)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T3_n7 -POSTHOOK: query: CREATE TABLE T3_n7(key STRING, val STRING) -SKEWED BY (val) ON ((12)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T3_n7 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n7 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t3_n7 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n7 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t3_n7 -PREHOOK: query: EXPLAIN -select * -from -T1_n29 a join T2_n20 b on a.key = b.key -join T3_n7 c on a.val = c.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n29 -PREHOOK: Input: default@t2_n20 -PREHOOK: Input: default@t3_n7 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -select * -from -T1_n29 a join T2_n20 b on a.key = b.key -join T3_n7 c on a.val = c.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n29 -POSTHOOK: Input: default@t2_n20 -POSTHOOK: Input: default@t3_n7 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-7 is a root stage - Stage-5 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-7 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - $hdt$_2:c - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_2:c - TableScan - alias: c - filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 444 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * -from -T1_n29 a join T2_n20 b on a.key = b.key -join T3_n7 c on a.val = c.val -order by a.key, b.key, c.key, a.val, b.val, c.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n29 -PREHOOK: Input: default@t2_n20 -PREHOOK: Input: default@t3_n7 -#### A masked pattern was here #### -POSTHOOK: query: select * -from -T1_n29 a join T2_n20 b on a.key = b.key -join T3_n7 c on a.val = c.val -order by a.key, b.key, c.key, a.val, b.val, c.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n29 -POSTHOOK: Input: default@t2_n20 -POSTHOOK: Input: default@t3_n7 -#### A masked pattern was here #### -2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out deleted file mode 100644 index 5035aa48f4..0000000000 --- ql/src/test/results/clientpositive/skewjoin_mapjoin9.q.out +++ /dev/null @@ -1,243 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n152(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n152 -POSTHOOK: query: CREATE TABLE T1_n152(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n152 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n152 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n152 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n152 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n152 -PREHOOK: query: CREATE TABLE T2_n89(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n89 -POSTHOOK: query: CREATE TABLE T2_n89(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n89 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n89 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n89 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n89 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n89 -PREHOOK: query: CREATE TABLE T3_n36(key STRING, val STRING) -SKEWED BY (val) ON ((12)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T3_n36 -POSTHOOK: query: CREATE TABLE T3_n36(key STRING, val STRING) -SKEWED BY (val) ON ((12)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T3_n36 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n36 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t3_n36 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n36 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t3_n36 -PREHOOK: query: EXPLAIN -select * -from -T1_n152 a join T2_n89 b on a.key = b.key -join T3_n36 c on a.val = c.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n152 -PREHOOK: Input: default@t2_n89 -PREHOOK: Input: default@t3_n36 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -select * -from -T1_n152 a join T2_n89 b on a.key = b.key -join T3_n36 c on a.val = c.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n152 -POSTHOOK: Input: default@t2_n89 -POSTHOOK: Input: default@t3_n36 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-10 is a root stage - Stage-7 depends on stages: Stage-10 - Stage-0 depends on stages: Stage-7 - -STAGE PLANS: - Stage: Stage-10 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - $hdt$_2:c - Fetch Operator - limit: -1 - subquery1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - filterExpr: (key is not null and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and val is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_2:c - TableScan - alias: c - filterExpr: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: val is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - subquery1:a - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and val is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (key = '2')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (key = '2'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * -from -T1_n152 a join T2_n89 b on a.key = b.key -join T3_n36 c on a.val = c.val -order by a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n152 -PREHOOK: Input: default@t2_n89 -PREHOOK: Input: default@t3_n36 -#### A masked pattern was here #### -POSTHOOK: query: select * -from -T1_n152 a join T2_n89 b on a.key = b.key -join T3_n36 c on a.val = c.val -order by a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n152 -POSTHOOK: Input: default@t2_n89 -POSTHOOK: Input: default@t3_n36 -#### A masked pattern was here #### -2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/skewjoin_noskew.q.out ql/src/test/results/clientpositive/skewjoin_noskew.q.out deleted file mode 100644 index 7cd81466e6..0000000000 --- ql/src/test/results/clientpositive/skewjoin_noskew.q.out +++ /dev/null @@ -1,257 +0,0 @@ -PREHOOK: query: explain -create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@noskew -POSTHOOK: query: explain -create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@noskew -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-8, Stage-2 - Stage-8 - Stage-6 depends on stages: Stage-8 - Stage-2 depends on stages: Stage-6 - Stage-0 depends on stages: Stage-2 - Stage-9 depends on stages: Stage-0, Stage-4 - Stage-3 depends on stages: Stage-9 - Stage-4 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - handleSkewJoin: true - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - 1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - 1 - TableScan - HashTable Sink Operator - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 30 - Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.noskew - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: col1, col2 - Statistics: Num rows: 30 Data size: 5340 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-9 - Create Table - columns: key string, value string - name: default.noskew - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat - serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.noskew - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@noskew -POSTHOOK: query: create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30 -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@noskew -POSTHOOK: Lineage: noskew.key SIMPLE [(src)a.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: noskew.value SIMPLE [(src)a.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from noskew -PREHOOK: type: QUERY -PREHOOK: Input: default@noskew -#### A masked pattern was here #### -POSTHOOK: query: select * from noskew -POSTHOOK: type: QUERY -POSTHOOK: Input: default@noskew -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -10 val_10 -100 val_100 -100 val_100 -100 val_100 -100 val_100 -103 val_103 -103 val_103 -103 val_103 -103 val_103 -104 val_104 -104 val_104 -104 val_104 -104 val_104 -105 val_105 -11 val_11 -111 val_111 -113 val_113 -113 val_113 -113 val_113 -113 val_113 -114 val_114 diff --git ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out deleted file mode 100644 index 75394dad06..0000000000 --- ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out +++ /dev/null @@ -1,295 +0,0 @@ -PREHOOK: query: DROP TABLE IF EXISTS skewtable -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS skewtable -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE skewtable (key STRING, value STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@skewtable -POSTHOOK: query: CREATE TABLE skewtable (key STRING, value STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@skewtable -PREHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@skewtable -POSTHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@skewtable -POSTHOOK: Lineage: skewtable.key SCRIPT [] -POSTHOOK: Lineage: skewtable.value SCRIPT [] -PREHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@skewtable -POSTHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@skewtable -POSTHOOK: Lineage: skewtable.key SCRIPT [] -POSTHOOK: Lineage: skewtable.value SCRIPT [] -PREHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@skewtable -POSTHOOK: query: INSERT INTO TABLE skewtable VALUES ("0", "val_0") -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@skewtable -POSTHOOK: Lineage: skewtable.key SCRIPT [] -POSTHOOK: Lineage: skewtable.value SCRIPT [] -PREHOOK: query: DROP TABLE IF EXISTS nonskewtable -PREHOOK: type: DROPTABLE -POSTHOOK: query: DROP TABLE IF EXISTS nonskewtable -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE nonskewtable (key STRING, value STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@nonskewtable -POSTHOOK: query: CREATE TABLE nonskewtable (key STRING, value STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@nonskewtable -PREHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("1", "val_1") -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@nonskewtable -POSTHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("1", "val_1") -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@nonskewtable -POSTHOOK: Lineage: nonskewtable.key SCRIPT [] -POSTHOOK: Lineage: nonskewtable.value SCRIPT [] -PREHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("2", "val_2") -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@nonskewtable -POSTHOOK: query: INSERT INTO TABLE nonskewtable VALUES ("2", "val_2") -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@nonskewtable -POSTHOOK: Lineage: nonskewtable.key SCRIPT [] -POSTHOOK: Lineage: nonskewtable.value SCRIPT [] -PREHOOK: query: EXPLAIN -CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@nonskewtable -PREHOOK: Input: default@skewtable -PREHOOK: Output: database:default -PREHOOK: Output: default@result_n1 -POSTHOOK: query: EXPLAIN -CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@nonskewtable -POSTHOOK: Input: default@skewtable -POSTHOOK: Output: database:default -POSTHOOK: Output: default@result_n1 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-6 depends on stages: Stage-1 , consists of Stage-7, Stage-0, Stage-3 - Stage-7 - Stage-5 depends on stages: Stage-7 - Stage-0 depends on stages: Stage-5 - Stage-8 depends on stages: Stage-0, Stage-3 - Stage-2 depends on stages: Stage-8 - Stage-3 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - handleSkewJoin: true - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.result_n1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: col1, col2 - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Conditional Operator - - Stage: Stage-7 - Map Reduce Local Work - Alias -> Map Local Tables: - 1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - 1 - TableScan - HashTable Sink Operator - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 reducesinkkey0 (type: string) - 1 reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.result_n1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: col1, col2 - Statistics: Num rows: 3 Data size: 522 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-8 - Create Table - columns: key string, value string - name: default.result_n1 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat - serde name: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.result_n1 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@nonskewtable -PREHOOK: Input: default@skewtable -PREHOOK: Output: database:default -PREHOOK: Output: default@result_n1 -POSTHOOK: query: CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@nonskewtable -POSTHOOK: Input: default@skewtable -POSTHOOK: Output: database:default -POSTHOOK: Output: default@result_n1 -POSTHOOK: Lineage: result_n1.key SIMPLE [(skewtable)a.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: result_n1.value SIMPLE [(skewtable)a.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: SELECT * FROM result_n1 -PREHOOK: type: QUERY -PREHOOK: Input: default@result_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM result_n1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@result_n1 -#### A masked pattern was here #### diff --git ql/src/test/results/clientpositive/skewjoin_union_remove_1.q.out ql/src/test/results/clientpositive/skewjoin_union_remove_1.q.out deleted file mode 100644 index 54d401c330..0000000000 --- ql/src/test/results/clientpositive/skewjoin_union_remove_1.q.out +++ /dev/null @@ -1,698 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n57(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n57 -POSTHOOK: query: CREATE TABLE T1_n57(key STRING, val STRING) -SKEWED BY (key) ON ((2)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n57 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n57 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n57 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n57 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n57 -PREHOOK: query: CREATE TABLE T2_n35(key STRING, val STRING) -SKEWED BY (key) ON ((3)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n35 -POSTHOOK: query: CREATE TABLE T2_n35(key STRING, val STRING) -SKEWED BY (key) ON ((3)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n35 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n35 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n35 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n35 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n35 -PREHOOK: query: EXPLAIN -SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-3 is a root stage - Stage-0 depends on stages: Stage-1, Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -PREHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-3 is a root stage - Stage-0 depends on stages: Stage-1, Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.* FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -ORDER BY a.key, b.key, a.val, b.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -NULL NULL 4 14 -NULL NULL 5 15 -PREHOOK: query: create table DEST1_n58(key1 STRING, val1 STRING, key2 STRING, val2 STRING) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@DEST1_n58 -POSTHOOK: query: create table DEST1_n58(key1 STRING, val1 STRING, key2 STRING, val2 STRING) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@DEST1_n58 -PREHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -PREHOOK: Output: default@dest1_n58 -POSTHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -POSTHOOK: Output: default@dest1_n58 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n58 - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n58 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n58 - -PREHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -PREHOOK: Output: default@dest1_n58 -POSTHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a JOIN T2_n35 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -POSTHOOK: Output: default@dest1_n58 -POSTHOOK: Lineage: dest1_n58.key1 SIMPLE [(t1_n57)a.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: dest1_n58.key2 SIMPLE [(t2_n35)b.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: dest1_n58.val1 SIMPLE [(t1_n57)a.FieldSchema(name:val, type:string, comment:null), ] -POSTHOOK: Lineage: dest1_n58.val2 SIMPLE [(t2_n35)b.FieldSchema(name:val, type:string, comment:null), ] -PREHOOK: query: SELECT * FROM DEST1_n58 -ORDER BY key1, key2, val1, val2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1_n58 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM DEST1_n58 -ORDER BY key1, key2, val1, val2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1_n58 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -PREHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -PREHOOK: Output: default@dest1_n58 -POSTHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -POSTHOOK: Output: default@dest1_n58 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key = '2') or (key = '3')) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n58 - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n58 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (not ((key = '2') or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1_n58 - -PREHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n57 -PREHOOK: Input: default@t2_n35 -PREHOOK: Output: default@dest1_n58 -POSTHOOK: query: INSERT OVERWRITE TABLE DEST1_n58 -SELECT * FROM T1_n57 a RIGHT OUTER JOIN T2_n35 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n57 -POSTHOOK: Input: default@t2_n35 -POSTHOOK: Output: default@dest1_n58 -POSTHOOK: Lineage: dest1_n58.key1 SIMPLE [(t1_n57)a.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: dest1_n58.key2 SIMPLE [(t2_n35)b.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: dest1_n58.val1 SIMPLE [(t1_n57)a.FieldSchema(name:val, type:string, comment:null), ] -POSTHOOK: Lineage: dest1_n58.val2 SIMPLE [(t2_n35)b.FieldSchema(name:val, type:string, comment:null), ] -PREHOOK: query: SELECT * FROM DEST1_n58 -ORDER BY key1, key2, val1, val2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1_n58 -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM DEST1_n58 -ORDER BY key1, key2, val1, val2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1_n58 -#### A masked pattern was here #### -2 12 2 22 -3 13 3 13 -8 18 8 18 -8 18 8 18 -8 28 8 18 -8 28 8 18 -NULL NULL 4 14 -NULL NULL 5 15 diff --git ql/src/test/results/clientpositive/skewjoin_union_remove_2.q.out ql/src/test/results/clientpositive/skewjoin_union_remove_2.q.out deleted file mode 100644 index 3793b85b43..0000000000 --- ql/src/test/results/clientpositive/skewjoin_union_remove_2.q.out +++ /dev/null @@ -1,260 +0,0 @@ -PREHOOK: query: CREATE TABLE T1_n8(key STRING, val STRING) -SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1_n8 -POSTHOOK: query: CREATE TABLE T1_n8(key STRING, val STRING) -SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T1_n8 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n8 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1_n8 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n8 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t1_n8 -PREHOOK: query: CREATE TABLE T2_n4(key STRING, val STRING) -SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2_n4 -POSTHOOK: query: CREATE TABLE T2_n4(key STRING, val STRING) -SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T2_n4 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n4 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t2_n4 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T2.txt' INTO TABLE T2_n4 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t2_n4 -PREHOOK: query: CREATE TABLE T3_n2(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T3_n2 -POSTHOOK: query: CREATE TABLE T3_n2(key STRING, val STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@T3_n2 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n2 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t3_n2 -POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T3.txt' INTO TABLE T3_n2 -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@t3_n2 -PREHOOK: query: EXPLAIN -SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n8 -PREHOOK: Input: default@t2_n4 -PREHOOK: Input: default@t3_n2 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n8 -POSTHOOK: Input: default@t2_n4 -POSTHOOK: Input: default@t3_n2 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-5 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) - TableScan - alias: c - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - Union - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 808 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: b - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key -ORDER BY a.key, b.key, c.key, a.val, b.val, c.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n8 -PREHOOK: Input: default@t2_n4 -PREHOOK: Input: default@t3_n2 -#### A masked pattern was here #### -POSTHOOK: query: SELECT a.*, b.*, c.* FROM T1_n8 a JOIN T2_n4 b ON a.key = b.key JOIN T3_n2 c on a.key = c.key -ORDER BY a.key, b.key, c.key, a.val, b.val, c.val -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n8 -POSTHOOK: Input: default@t2_n4 -POSTHOOK: Input: default@t3_n2 -#### A masked pattern was here #### -2 12 2 22 2 12 diff --git ql/src/test/results/clientpositive/stat_estimate_drill.q.out ql/src/test/results/clientpositive/stat_estimate_drill.q.out deleted file mode 100644 index e95ae413d0..0000000000 --- ql/src/test/results/clientpositive/stat_estimate_drill.q.out +++ /dev/null @@ -1,569 +0,0 @@ -PREHOOK: query: drop table if exists t1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table if exists t1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table if exists t8 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table if exists t8 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table t1 (a integer) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t1 -POSTHOOK: query: create table t1 (a integer) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t1 -PREHOOK: query: create table t3 (a integer,b integer,c integer) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t3 -POSTHOOK: query: create table t3 (a integer,b integer,c integer) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t3 -PREHOOK: query: insert into t1 values (1),(2),(3),(4),(5),(6),(7),(8),(9),(0) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t1 -POSTHOOK: query: insert into t1 values (1),(2),(3),(4),(5),(6),(7),(8),(9),(0) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t1 -POSTHOOK: Lineage: t1.a SCRIPT [] -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: insert into t3 - select x1.a as a,x2.a as b,x3.a as c from - t1 x1 - join t1 x2 - join t1 x3 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Output: default@t3 -POSTHOOK: query: insert into t3 - select x1.a as a,x2.a as b,x3.a as c from - t1 x1 - join t1 x2 - join t1 x3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -POSTHOOK: Output: default@t3 -POSTHOOK: Lineage: t3.a SIMPLE [(t1)x1.FieldSchema(name:a, type:int, comment:null), ] -POSTHOOK: Lineage: t3.b SIMPLE [(t1)x2.FieldSchema(name:a, type:int, comment:null), ] -POSTHOOK: Lineage: t3.c SIMPLE [(t1)x3.FieldSchema(name:a, type:int, comment:null), ] -PREHOOK: query: analyze table t3 compute statistics for columns -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@t3 -PREHOOK: Output: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: analyze table t3 compute statistics for columns -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@t3 -POSTHOOK: Output: default@t3 -#### A masked pattern was here #### -PREHOOK: query: select sum(a) from t3 where b in (2,3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t3 where b in (2,3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t3 where b in (2,3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t3 where b in (2,3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t3 - filterExpr: (b) IN (2, 3) (type: boolean) - Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (b) IN (2, 3) (type: boolean) - Statistics: Num rows: 200/200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: b (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 2/2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2/2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t3 where a=1 or a=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t3 where a=1 or a=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t3 where a=1 or a=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 or a=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t3 - filterExpr: (a) IN (1, 2) (type: boolean) - Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (a) IN (1, 2) (type: boolean) - Statistics: Num rows: 200/200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: b (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t3 where a=1 or (a=2 and b=3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t3 where a=1 or (a=2 and b=3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t3 where a=1 or (a=2 and b=3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 or (a=2 and b=3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t3 - filterExpr: ((a = 1) or ((a = 2) and (b = 3))) (type: boolean) - Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((a = 1) or ((a = 2) and (b = 3))) (type: boolean) - Statistics: Num rows: 110/110 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: b (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t3 where a=1 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t3 where a=1 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t3 where a=1 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t3 - filterExpr: (a = 1) (type: boolean) - Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (a = 1) (type: boolean) - Statistics: Num rows: 100/100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: b (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 100/100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(1) - keys: _col0 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t3 where a=1 and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t3 where a=1 and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t3 - filterExpr: ((a = 1) and (b = 2)) (type: boolean) - Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((a = 1) and (b = 2)) (type: boolean) - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(1) - keys: true (type: boolean) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: boolean) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: boolean) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t3 where a=1 and b=2 and c=3 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t3 where a=1 and b=2 and c=3 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 and c=3 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 and c=3 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t3 - filterExpr: ((a = 1) and (b = 2) and (c = 3)) (type: boolean) - Statistics: Num rows: 1000/1000 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((a = 1) and (b = 2) and (c = 3)) (type: boolean) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(1) - keys: true (type: boolean) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: boolean) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: boolean) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: boolean) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t3 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t3 - filterExpr: (struct(a,b)) IN (const struct(1,2), const struct(2,3), const struct(3,4)) (type: boolean) - Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (struct(a,b)) IN (const struct(1,2), const struct(2,3), const struct(3,4)) (type: boolean) - Statistics: Num rows: 30/30 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: b (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10/3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10/3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 10/3 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10/3 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/stat_estimate_related_col.q.out ql/src/test/results/clientpositive/stat_estimate_related_col.q.out deleted file mode 100644 index a4f2fe472c..0000000000 --- ql/src/test/results/clientpositive/stat_estimate_related_col.q.out +++ /dev/null @@ -1,857 +0,0 @@ -PREHOOK: query: drop table if exists t1 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table if exists t1 -POSTHOOK: type: DROPTABLE -PREHOOK: query: drop table if exists t8 -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table if exists t8 -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table t1 (a integer,b integer) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t1 -POSTHOOK: query: create table t1 (a integer,b integer) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t1 -PREHOOK: query: create table t8 like t1 -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t8 -POSTHOOK: query: create table t8 like t1 -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t8 -PREHOOK: query: insert into t1 values (1,1),(2,2),(3,3),(4,4),(5,5) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t1 -POSTHOOK: query: insert into t1 values (1,1),(2,2),(3,3),(4,4),(5,5) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t1 -POSTHOOK: Lineage: t1.a SCRIPT [] -POSTHOOK: Lineage: t1.b SCRIPT [] -PREHOOK: query: insert into t8 -select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 union all -select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Output: default@t8 -POSTHOOK: query: insert into t8 -select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 union all -select * from t1 union all select * from t1 union all select * from t1 union all select * from t1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -POSTHOOK: Output: default@t8 -POSTHOOK: Lineage: t8.a EXPRESSION [(t1)t1.FieldSchema(name:a, type:int, comment:null), ] -POSTHOOK: Lineage: t8.b EXPRESSION [(t1)t1.FieldSchema(name:b, type:int, comment:null), ] -PREHOOK: query: analyze table t1 compute statistics for columns -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@t1 -PREHOOK: Output: default@t1 -#### A masked pattern was here #### -POSTHOOK: query: analyze table t1 compute statistics for columns -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@t1 -POSTHOOK: Output: default@t1 -#### A masked pattern was here #### -PREHOOK: query: analyze table t8 compute statistics for columns -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@t8 -PREHOOK: Output: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: analyze table t8 compute statistics for columns -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@t8 -POSTHOOK: Output: default@t8 -#### A masked pattern was here #### -PREHOOK: query: select sum(a) from t8 where b in (2,3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t8 where b in (2,3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t8 - filterExpr: (b) IN (2, 3) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (b) IN (2, 3) (type: boolean) - Statistics: Num rows: 16/16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: b (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 2/2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2/2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t8 where b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t8 where b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t8 where b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t8 where b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t8 - filterExpr: (b = 2) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (b = 2) (type: boolean) - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: a - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t1 where 2=b and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t1 where 2=b and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t1 where 2=b and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t1 where 2=b and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((2 = b) and (b = 2)) (type: boolean) - Statistics: Num rows: 5/5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((2 = b) and (b = 2)) (type: boolean) - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: a - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t1 where b in (2,3) and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t1 where b in (2,3) and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t1 where b in (2,3) and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t1 where b in (2,3) and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - filterExpr: ((b) IN (2, 3) and (b = 2)) (type: boolean) - Statistics: Num rows: 5/5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((b) IN (2, 3) and (b = 2)) (type: boolean) - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: a - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t8 where b in (2,3) and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t8 where b in (2,3) and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) and b=2 group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t8 where b in (2,3) and b=2 group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t8 - filterExpr: ((b) IN (2, 3) and (b = 2)) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((b) IN (2, 3) and (b = 2)) (type: boolean) - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: a - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ta - filterExpr: (a = 3) (type: boolean) - Statistics: Num rows: 40/40 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (a = 3) (type: boolean) - Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 3 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 3 (type: int) - Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: tb - filterExpr: (b = 3) (type: boolean) - Statistics: Num rows: 40/40 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (b = 3) (type: boolean) - Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 3 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 3 (type: int) - Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 a (type: int) - 1 b (type: int) - Statistics: Num rows: 64/64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t8 where b in (1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50) and b=2 and b=2 and 2=b group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t8 - filterExpr: ((b) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50) and (b = 2) and (2 = b)) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((b) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50) and (b = 2) and (2 = b)) (type: boolean) - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: a - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t8 - filterExpr: ((b = 2) and ((b = 1) or (b = 2))) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((b = 2) and ((b = 1) or (b = 2))) (type: boolean) - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: a - Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t8 where b=2 and (b = 1 or b=2) and (b=1 or b=3) group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t8 - filterExpr: ((b = 2) and ((b = 1) or (b = 2)) and ((b = 1) or (b = 3))) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((b = 2) and ((b = 1) or (b = 2)) and ((b = 1) or (b = 3))) (type: boolean) - Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: a (type: int) - outputColumnNames: a - Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/0 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/0 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select sum(a) from t8 where - b=2 and (b = 1 or b=2) -and - a=3 and (a = 3 or a=4) -group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: select sum(a) from t8 where - b=2 and (b = 1 or b=2) -and - a=3 and (a = 3 or a=4) -group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -PREHOOK: query: explain analyze select sum(a) from t8 where - b=2 and (b = 1 or b=2) -and - a=3 and (a = 3 or a=4) -group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@t8 -#### A masked pattern was here #### -POSTHOOK: query: explain analyze select sum(a) from t8 where - b=2 and (b = 1 or b=2) -and - a=3 and (a = 3 or a=4) -group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t8 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t8 - filterExpr: ((b = 2) and ((b = 1) or (b = 2)) and (a = 3) and ((a = 3) or (a = 4))) (type: boolean) - Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((b = 2) and ((b = 1) or (b = 2)) and (a = 3) and ((a = 3) or (a = 4))) (type: boolean) - Statistics: Num rows: 2/0 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 3 (type: int) - outputColumnNames: a - Statistics: Num rows: 2/0 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: 2 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: 2 (type: int) - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: 2 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1/0 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1/0 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out deleted file mode 100644 index 85b2d21b6c..0000000000 --- ql/src/test/results/clientpositive/stats_empty_dyn_part.q.out +++ /dev/null @@ -1,151 +0,0 @@ -PREHOOK: query: create table tmptable_n7(key string) partitioned by (part string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tmptable_n7 -POSTHOOK: query: create table tmptable_n7(key string) partitioned by (part string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tmptable_n7 -PREHOOK: query: explain insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tmptable_n7 -POSTHOOK: query: explain insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (key = 'no_such_value') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key = 'no_such_value') (type: boolean) - Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'no_such_value' (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n7 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, part - Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll') - keys: part (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 531 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - partition: - part - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n7 - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key - Column Types: string - Table: default.tmptable_n7 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n7 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tmptable_n7 - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tmptable_n7 -POSTHOOK: query: insert overwrite table tmptable_n7 partition (part) select key, value from src where key = 'no_such_value' -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src diff --git ql/src/test/results/clientpositive/stats_partial_size.q.out ql/src/test/results/clientpositive/stats_partial_size.q.out deleted file mode 100644 index 191a3d4d89..0000000000 --- ql/src/test/results/clientpositive/stats_partial_size.q.out +++ /dev/null @@ -1,114 +0,0 @@ -PREHOOK: query: create table sample_partitioned (x int) partitioned by (y int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@sample_partitioned -POSTHOOK: query: create table sample_partitioned (x int) partitioned by (y int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@sample_partitioned -PREHOOK: query: insert into sample_partitioned partition(y=1) values (1),(2) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@sample_partitioned@y=1 -POSTHOOK: query: insert into sample_partitioned partition(y=1) values (1),(2) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@sample_partitioned@y=1 -POSTHOOK: Lineage: sample_partitioned PARTITION(y=1).x SCRIPT [] -PREHOOK: query: create temporary table sample as select * from sample_partitioned -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@sample_partitioned -PREHOOK: Input: default@sample_partitioned@y=1 -PREHOOK: Output: database:default -PREHOOK: Output: default@sample -POSTHOOK: query: create temporary table sample as select * from sample_partitioned -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@sample_partitioned -POSTHOOK: Input: default@sample_partitioned@y=1 -POSTHOOK: Output: database:default -POSTHOOK: Output: default@sample -PREHOOK: query: analyze table sample compute statistics for columns -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@sample -PREHOOK: Output: default@sample -#### A masked pattern was here #### -POSTHOOK: query: analyze table sample compute statistics for columns -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@sample -POSTHOOK: Output: default@sample -#### A masked pattern was here #### -PREHOOK: query: explain select sample_partitioned.x from sample_partitioned, sample where sample.y = sample_partitioned.y -PREHOOK: type: QUERY -PREHOOK: Input: default@sample -PREHOOK: Input: default@sample_partitioned -PREHOOK: Input: default@sample_partitioned@y=1 -#### A masked pattern was here #### -POSTHOOK: query: explain select sample_partitioned.x from sample_partitioned, sample where sample.y = sample_partitioned.y -POSTHOOK: type: QUERY -POSTHOOK: Input: default@sample -POSTHOOK: Input: default@sample_partitioned -POSTHOOK: Input: default@sample_partitioned@y=1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: sample_partitioned - filterExpr: y is not null (type: boolean) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: x (type: int), y (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - TableScan - alias: sample - filterExpr: y is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: y is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: y (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/stats_ppr_all.q.out ql/src/test/results/clientpositive/stats_ppr_all.q.out deleted file mode 100644 index 8eaa729be2..0000000000 --- ql/src/test/results/clientpositive/stats_ppr_all.q.out +++ /dev/null @@ -1,341 +0,0 @@ -PREHOOK: query: drop table ss -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table ss -POSTHOOK: type: DROPTABLE -PREHOOK: query: CREATE TABLE ss ( - sales_order_id BIGINT, - order_amount FLOAT) -PARTITIONED BY (country STRING, year INT, month INT, day INT) stored as orc -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@ss -POSTHOOK: query: CREATE TABLE ss ( - sales_order_id BIGINT, - order_amount FLOAT) -PARTITIONED BY (country STRING, year INT, month INT, day INT) stored as orc -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@ss -PREHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=1) values(1,22.0) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 -POSTHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=1) values(1,22.0) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 -POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=1).order_amount SCRIPT [] -POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=1).sales_order_id SCRIPT [] -PREHOOK: query: insert into ss partition(country="US", year=2015, month=2, day=1) values(2,2.0) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 -POSTHOOK: query: insert into ss partition(country="US", year=2015, month=2, day=1) values(2,2.0) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 -POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=2,day=1).order_amount SCRIPT [] -POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=2,day=1).sales_order_id SCRIPT [] -PREHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=2) values(1,2.0) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 -POSTHOOK: query: insert into ss partition(country="US", year=2015, month=1, day=2) values(1,2.0) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 -POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=2).order_amount SCRIPT [] -POSTHOOK: Lineage: ss PARTITION(country=US,year=2015,month=1,day=2).sales_order_id SCRIPT [] -PREHOOK: query: ANALYZE TABLE ss PARTITION(country,year,month,day) compute statistics for columns -PREHOOK: type: ANALYZE_TABLE -PREHOOK: Input: default@ss -PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 -PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 -PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -PREHOOK: Output: default@ss -PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 -PREHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 -PREHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -POSTHOOK: query: ANALYZE TABLE ss PARTITION(country,year,month,day) compute statistics for columns -POSTHOOK: type: ANALYZE_TABLE -POSTHOOK: Input: default@ss -POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 -POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 -POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -POSTHOOK: Output: default@ss -POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=1 -POSTHOOK: Output: default@ss@country=US/year=2015/month=1/day=2 -POSTHOOK: Output: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -PREHOOK: query: explain select sum(order_amount) from ss where (country="US" and year=2015 and month=2 and day=1) -PREHOOK: type: QUERY -PREHOOK: Input: default@ss -PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(order_amount) from ss where (country="US" and year=2015 and month=2 and day=1) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ss -POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ss - filterExpr: ((country = 'US') and (year = 2015) and (month = 2) and (day = 1)) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: order_amount (type: float) - outputColumnNames: order_amount - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(order_amount) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select sum(order_amount) from ss where (year*10000+month*100+day) = "2015010" and 1>0 -PREHOOK: type: QUERY -PREHOOK: Input: default@ss -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(order_amount) from ss where (year*10000+month*100+day) = "2015010" and 1>0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ss -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ss - filterExpr: (UDFToDouble((((year * 10000) + (month * 100)) + day)) = 2015010.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble((((year * 10000) + (month * 100)) + day)) = 2015010.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: order_amount (type: float) - outputColumnNames: order_amount - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(order_amount) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) = "201511" and 1>0 -PREHOOK: type: QUERY -PREHOOK: Input: default@ss -PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) = "201511" and 1>0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ss -POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ss - filterExpr: (201511.0D = 201511.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: order_amount (type: float) - outputColumnNames: order_amount - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(order_amount) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) > "201511" and 1>0 -PREHOOK: type: QUERY -PREHOOK: Input: default@ss -PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 -PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -POSTHOOK: query: explain select sum(order_amount) from ss where (year*100+month*10+day) > "201511" and 1>0 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ss -POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 -POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ss - filterExpr: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) - Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: order_amount (type: float) - outputColumnNames: order_amount - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(order_amount) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select '1' from ss where (year*100+month*10+day) > "201511" -PREHOOK: type: QUERY -PREHOOK: Input: default@ss -PREHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 -PREHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -POSTHOOK: query: explain select '1' from ss where (year*100+month*10+day) > "201511" -POSTHOOK: type: QUERY -POSTHOOK: Input: default@ss -POSTHOOK: Input: default@ss@country=US/year=2015/month=1/day=2 -POSTHOOK: Input: default@ss@country=US/year=2015/month=2/day=1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: ss - filterExpr: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(((201500 + (month * 10)) + day)) > 201511.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: '1' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - diff --git ql/src/test/results/clientpositive/subq.q.out ql/src/test/results/clientpositive/subq.q.out deleted file mode 100644 index 017c6d4f38..0000000000 --- ql/src/test/results/clientpositive/subq.q.out +++ /dev/null @@ -1,190 +0,0 @@ -PREHOOK: query: EXPLAIN -FROM ( - FROM src select src.* WHERE src.key < 100 -) unioninput -INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: target/warehouse/union.out -POSTHOOK: query: EXPLAIN -FROM ( - FROM src select src.* WHERE src.key < 100 -) unioninput -INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: target/warehouse/union.out -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-6 depends on stages: Stage-1 , consists of Stage-3, Stage-2, Stage-4 - Stage-3 - Stage-0 depends on stages: Stage-3, Stage-2, Stage-5 - Stage-2 - Stage-4 - Stage-5 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (UDFToDouble(key) < 100.0D) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - - Stage: Stage-6 - Conditional Operator - - Stage: Stage-3 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - files: - hdfs directory: true - destination: target/warehouse/union.out - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: FROM ( - FROM src select src.* WHERE src.key < 100 -) unioninput -INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: target/warehouse/union.out -POSTHOOK: query: FROM ( - FROM src select src.* WHERE src.key < 100 -) unioninput -INSERT OVERWRITE DIRECTORY 'target/warehouse/union.out' SELECT unioninput.* -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: target/warehouse/union.out -86val_86 -27val_27 -98val_98 -66val_66 -37val_37 -15val_15 -82val_82 -17val_17 -0val_0 -57val_57 -20val_20 -92val_92 -47val_47 -72val_72 -4val_4 -35val_35 -54val_54 -51val_51 -65val_65 -83val_83 -12val_12 -67val_67 -84val_84 -58val_58 -8val_8 -24val_24 -42val_42 -0val_0 -96val_96 -26val_26 -51val_51 -43val_43 -95val_95 -98val_98 -85val_85 -77val_77 -0val_0 -87val_87 -15val_15 -72val_72 -90val_90 -19val_19 -10val_10 -5val_5 -58val_58 -35val_35 -95val_95 -11val_11 -34val_34 -42val_42 -78val_78 -76val_76 -41val_41 -30val_30 -64val_64 -76val_76 -74val_74 -69val_69 -33val_33 -70val_70 -5val_5 -2val_2 -35val_35 -80val_80 -44val_44 -53val_53 -90val_90 -12val_12 -5val_5 -70val_70 -24val_24 -70val_70 -83val_83 -26val_26 -67val_67 -18val_18 -9val_9 -18val_18 -97val_97 -84val_84 -28val_28 -37val_37 -90val_90 -97val_97 diff --git ql/src/test/results/clientpositive/subq_where_serialization.q.out ql/src/test/results/clientpositive/subq_where_serialization.q.out deleted file mode 100644 index bda4280eb2..0000000000 --- ql/src/test/results/clientpositive/subq_where_serialization.q.out +++ /dev/null @@ -1,83 +0,0 @@ -PREHOOK: query: explain select src.key from src where src.key in ( select distinct key from src) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select src.key from src where src.key in ( select distinct key from src) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-3 depends on stages: Stage-4 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-4 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:src - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:src - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/subquery_exists_having.q.out ql/src/test/results/clientpositive/subquery_exists_having.q.out deleted file mode 100644 index dfe2f9f0ef..0000000000 --- ql/src/test/results/clientpositive/subquery_exists_having.q.out +++ /dev/null @@ -1,410 +0,0 @@ -PREHOOK: query: explain -select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - TableScan - alias: a - filterExpr: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -90 3 -92 1 -95 2 -96 1 -97 2 -98 2 -PREHOOK: query: explain -select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - TableScan - alias: a - filterExpr: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((value > 'val_9') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 333 Data size: 30971 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Mux Operator - Statistics: Num rows: 583 Data size: 54721 Basic stats: COMPLETE Column stats: COMPLETE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Mux Operator - Statistics: Num rows: 583 Data size: 54721 Basic stats: COMPLETE Column stats: COMPLETE - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 641 Data size: 60193 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select b.key, count(*) -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -90 3 -92 1 -95 2 -96 1 -97 2 -98 2 -PREHOOK: query: create view cv1_n6 as -select b.key, count(*) as c -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -PREHOOK: type: CREATEVIEW -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@cv1_n6 -POSTHOOK: query: create view cv1_n6 as -select b.key, count(*) as c -from src b -group by b.key -having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -POSTHOOK: type: CREATEVIEW -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@cv1_n6 -POSTHOOK: Lineage: cv1_n6.c EXPRESSION [(src)b.null, ] -POSTHOOK: Lineage: cv1_n6.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -PREHOOK: query: select * from cv1_n6 -PREHOOK: type: QUERY -PREHOOK: Input: default@cv1_n6 -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * from cv1_n6 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@cv1_n6 -POSTHOOK: Input: default@src -#### A masked pattern was here #### -90 3 -92 1 -95 2 -96 1 -97 2 -98 2 -PREHOOK: query: select * -from (select b.key, count(*) - from src b - group by b.key - having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -) a -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * -from (select b.key, count(*) - from src b - group by b.key - having exists - (select a.key - from src a - where a.key = b.key and a.value > 'val_9' - ) -) a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -90 3 -92 1 -95 2 -96 1 -97 2 -98 2 -PREHOOK: query: select b.key, min(b.value) -from src b -group by b.key -having exists ( select a.key - from src a - where a.value > 'val_9' and a.value = min(b.value) - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select b.key, min(b.value) -from src b -group by b.key -having exists ( select a.key - from src a - where a.value > 'val_9' and a.value = min(b.value) - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -90 val_90 -92 val_92 -95 val_95 -96 val_96 -97 val_97 -98 val_98 diff --git ql/src/test/results/clientpositive/subquery_multiinsert.q.out ql/src/test/results/clientpositive/subquery_multiinsert.q.out deleted file mode 100644 index d3e2750fb7..0000000000 --- ql/src/test/results/clientpositive/subquery_multiinsert.q.out +++ /dev/null @@ -1,1187 +0,0 @@ -PREHOOK: query: CREATE TABLE src_4( - key STRING, - value STRING -) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_4 -POSTHOOK: query: CREATE TABLE src_4( - key STRING, - value STRING -) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_4 -RUN: Stage-0:DDL -PREHOOK: query: CREATE TABLE src_5( - key STRING, - value STRING -) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_5 -POSTHOOK: query: CREATE TABLE src_5( - key STRING, - value STRING -) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_5 -RUN: Stage-0:DDL -Warning: Shuffle Join JOIN[38][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_4 -PREHOOK: Output: default@src_5 -POSTHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_4 -POSTHOOK: Output: default@src_5 -STAGE DEPENDENCIES: - Stage-11 is a root stage - Stage-2 depends on stages: Stage-11 - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1, Stage-8 - Stage-6 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-6 - Stage-7 depends on stages: Stage-0, Stage-8 - Stage-8 depends on stages: Stage-6 - -STAGE PLANS: - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - alias: s1 - filterExpr: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 = 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: 0L (type: bigint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: key (type: string), value (type: string) - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - TableScan - alias: s1 - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 762 Data size: 158517 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col5 is null (type: boolean) - Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: struct), _col1 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_5 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_5 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: key (type: string), value (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: a - filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 key (type: string), value (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_4 - - Stage: Stage-7 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_4 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -Warning: Shuffle Join JOIN[38][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_4 -PREHOOK: Output: default@src_5 -POSTHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_4 -POSTHOOK: Output: default@src_5 -POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -RUN: Stage-11:MAPRED -RUN: Stage-2:MAPRED -RUN: Stage-3:MAPRED -RUN: Stage-6:MAPRED -RUN: Stage-4:MAPRED -RUN: Stage-0:MOVE -RUN: Stage-8:MAPRED -RUN: Stage-1:MOVE -RUN: Stage-7:STATS -RUN: Stage-5:STATS -PREHOOK: query: select * from src_4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_4 -#### A masked pattern was here #### -90 val_90 -90 val_90 -90 val_90 -92 val_92 -95 val_95 -95 val_95 -96 val_96 -97 val_97 -97 val_97 -98 val_98 -98 val_98 -PREHOOK: query: select * from src_5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_5 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -10 val_10 -100 val_100 -100 val_100 -103 val_103 -103 val_103 -104 val_104 -104 val_104 -105 val_105 -11 val_11 -111 val_111 -113 val_113 -113 val_113 -114 val_114 -116 val_116 -118 val_118 -118 val_118 -119 val_119 -119 val_119 -119 val_119 -12 val_12 -12 val_12 -120 val_120 -120 val_120 -125 val_125 -125 val_125 -126 val_126 -128 val_128 -128 val_128 -128 val_128 -129 val_129 -129 val_129 -131 val_131 -133 val_133 -134 val_134 -134 val_134 -136 val_136 -137 val_137 -137 val_137 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -143 val_143 -145 val_145 -146 val_146 -146 val_146 -149 val_149 -149 val_149 -15 val_15 -15 val_15 -150 val_150 -152 val_152 -152 val_152 -153 val_153 -155 val_155 -156 val_156 -157 val_157 -158 val_158 -160 val_160 -162 val_162 -163 val_163 -164 val_164 -164 val_164 -165 val_165 -165 val_165 -166 val_166 -167 val_167 -167 val_167 -167 val_167 -168 val_168 -169 val_169 -169 val_169 -169 val_169 -169 val_169 -17 val_17 -170 val_170 -172 val_172 -172 val_172 -174 val_174 -174 val_174 -175 val_175 -175 val_175 -176 val_176 -176 val_176 -177 val_177 -178 val_178 -179 val_179 -179 val_179 -18 val_18 -18 val_18 -180 val_180 -181 val_181 -183 val_183 -186 val_186 -187 val_187 -187 val_187 -187 val_187 -189 val_189 -19 val_19 -190 val_190 -191 val_191 -191 val_191 -192 val_192 -193 val_193 -193 val_193 -193 val_193 -194 val_194 -195 val_195 -195 val_195 -196 val_196 -197 val_197 -197 val_197 -199 val_199 -199 val_199 -199 val_199 -2 val_2 -Warning: Map Join MAPJOIN[80][bigTable=b] in task 'Stage-14:MAPRED' is a cross product -Warning: Shuffle Join JOIN[38][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_4 -PREHOOK: Output: default@src_5 -POSTHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_4 -POSTHOOK: Output: default@src_5 -STAGE DEPENDENCIES: - Stage-11 is a root stage - Stage-15 depends on stages: Stage-11 , consists of Stage-18, Stage-2 - Stage-18 has a backup stage: Stage-2 - Stage-14 depends on stages: Stage-18 - Stage-16 depends on stages: Stage-2, Stage-14 - Stage-4 depends on stages: Stage-16 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1, Stage-8 - Stage-17 depends on stages: Stage-2, Stage-14 - Stage-13 depends on stages: Stage-17 - Stage-0 depends on stages: Stage-13 - Stage-7 depends on stages: Stage-0, Stage-8 - Stage-8 depends on stages: Stage-13 - Stage-2 - -STAGE PLANS: - Stage: Stage-11 - Map Reduce - Map Operator Tree: - TableScan - alias: s1 - filterExpr: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 = 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: 0L (type: bigint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-15 - Conditional Operator - - Stage: Stage-18 - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME - TableScan - HashTable Sink Operator - keys: - 0 - 1 - - Stage: Stage-14 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-16 - Map Reduce Local Work - Alias -> Map Local Tables: - sq_2:s1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - sq_2:s1 - TableScan - alias: s1 - filterExpr: (key > '2') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 762 Data size: 158517 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col5 is null (type: boolean) - Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Statistics: Num rows: 500 Data size: 104051 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_5 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: struct), _col1 (type: struct) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_5 - - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_5 - - Stage: Stage-17 - Map Reduce Local Work - Alias -> Map Local Tables: - sq_1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - sq_1:a - TableScan - alias: a - filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - HashTable Sink Operator - keys: - 0 key (type: string), value (type: string) - 1 _col0 (type: string), _col1 (type: string) - - Stage: Stage-13 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 key (type: string), value (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_4 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_4 - - Stage: Stage-7 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.src_4 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: key (type: string), value (type: string) - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - -Warning: Map Join MAPJOIN[80][bigTable=b] in task 'Stage-14:MAPRED' is a cross product -Warning: Shuffle Join JOIN[38][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_4 -PREHOOK: Output: default@src_5 -POSTHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_4 -POSTHOOK: Output: default@src_5 -POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -RUN: Stage-11:MAPRED -RUN: Stage-15:CONDITIONAL -RUN: Stage-18:MAPREDLOCAL -RUN: Stage-14:MAPRED -RUN: Stage-16:MAPREDLOCAL -RUN: Stage-17:MAPREDLOCAL -RUN: Stage-4:MAPRED -RUN: Stage-13:MAPRED -RUN: Stage-1:MOVE -RUN: Stage-0:MOVE -RUN: Stage-8:MAPRED -RUN: Stage-5:STATS -RUN: Stage-7:STATS -PREHOOK: query: select * from src_4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_4 -#### A masked pattern was here #### -90 val_90 -90 val_90 -90 val_90 -92 val_92 -95 val_95 -95 val_95 -96 val_96 -97 val_97 -97 val_97 -98 val_98 -98 val_98 -PREHOOK: query: select * from src_5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_5 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -10 val_10 -100 val_100 -100 val_100 -103 val_103 -103 val_103 -104 val_104 -104 val_104 -105 val_105 -11 val_11 -111 val_111 -113 val_113 -113 val_113 -114 val_114 -116 val_116 -118 val_118 -118 val_118 -119 val_119 -119 val_119 -119 val_119 -12 val_12 -12 val_12 -120 val_120 -120 val_120 -125 val_125 -125 val_125 -126 val_126 -128 val_128 -128 val_128 -128 val_128 -129 val_129 -129 val_129 -131 val_131 -133 val_133 -134 val_134 -134 val_134 -136 val_136 -137 val_137 -137 val_137 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -143 val_143 -145 val_145 -146 val_146 -146 val_146 -149 val_149 -149 val_149 -15 val_15 -15 val_15 -150 val_150 -152 val_152 -152 val_152 -153 val_153 -155 val_155 -156 val_156 -157 val_157 -158 val_158 -160 val_160 -162 val_162 -163 val_163 -164 val_164 -164 val_164 -165 val_165 -165 val_165 -166 val_166 -167 val_167 -167 val_167 -167 val_167 -168 val_168 -169 val_169 -169 val_169 -169 val_169 -169 val_169 -17 val_17 -170 val_170 -172 val_172 -172 val_172 -174 val_174 -174 val_174 -175 val_175 -175 val_175 -176 val_176 -176 val_176 -177 val_177 -178 val_178 -179 val_179 -179 val_179 -18 val_18 -18 val_18 -180 val_180 -181 val_181 -183 val_183 -186 val_186 -187 val_187 -187 val_187 -187 val_187 -189 val_189 -19 val_19 -190 val_190 -191 val_191 -191 val_191 -192 val_192 -193 val_193 -193 val_193 -193 val_193 -194 val_194 -195 val_195 -195 val_195 -196 val_196 -197 val_197 -197 val_197 -199 val_199 -199 val_199 -199 val_199 -2 val_2 diff --git ql/src/test/results/clientpositive/subquery_notexists_having.q.out ql/src/test/results/clientpositive/subquery_notexists_having.q.out deleted file mode 100644 index ae9da6470f..0000000000 --- ql/src/test/results/clientpositive/subquery_notexists_having.q.out +++ /dev/null @@ -1,396 +0,0 @@ -PREHOOK: query: explain -select * -from src b -group by key, value -having not exists - (select a.key - from src a - where b.value = a.value and a.key = b.key and a.value > 'val_12' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select * -from src b -group by key, value -having not exists - (select a.key - from src a - where b.value = a.value and a.key = b.key and a.value > 'val_12' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 333 Data size: 59610 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 250 Data size: 44752 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((value > 'val_12') and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((value > 'val_12') and key is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: string), value (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: true (type: boolean), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * -from src b -group by key, value -having not exists - (select a.key - from src a - where b.value = a.value and a.key = b.key and a.value > 'val_12' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * -from src b -group by key, value -having not exists - (select a.key - from src a - where b.value = a.value and a.key = b.key and a.value > 'val_12' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 -10 val_10 -100 val_100 -103 val_103 -104 val_104 -105 val_105 -11 val_11 -111 val_111 -113 val_113 -114 val_114 -116 val_116 -118 val_118 -119 val_119 -12 val_12 -PREHOOK: query: explain -select * -from src b -group by key, value -having not exists - (select distinct a.key - from src a - where b.value = a.value and a.value > 'val_12' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select * -from src b -group by key, value -having not exists - (select distinct a.key - from src a - where b.value = a.value and a.value > 'val_12' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-3 - Stage-3 is a root stage - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: value (type: string), key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 333 Data size: 59610 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 250 Data size: 44752 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: (value > 'val_12') (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (value > 'val_12') (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: value (type: string), key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col1 (type: string) - mode: complete - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * -from src b -group by key, value -having not exists - (select distinct a.key - from src a - where b.value = a.value and a.value > 'val_12' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * -from src b -group by key, value -having not exists - (select distinct a.key - from src a - where b.value = a.value and a.value > 'val_12' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -0 val_0 -10 val_10 -100 val_100 -103 val_103 -104 val_104 -105 val_105 -11 val_11 -111 val_111 -113 val_113 -114 val_114 -116 val_116 -118 val_118 -119 val_119 -12 val_12 diff --git ql/src/test/results/clientpositive/subquery_notin_having.q.out ql/src/test/results/clientpositive/subquery_notin_having.q.out deleted file mode 100644 index 8c2c09a685..0000000000 --- ql/src/test/results/clientpositive/subquery_notin_having.q.out +++ /dev/null @@ -1,1421 +0,0 @@ -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product -PREHOOK: query: explain -select key, count(*) -from src -group by key -having key not in - ( select key from src s1 - where s1.key > '12' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select key, count(*) -from src -group by key -having key not in - ( select key from src s1 - where s1.key > '12' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2, Stage-5 - Stage-4 is a root stage - Stage-5 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 333 Data size: 31971 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 333 Data size: 31971 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: boolean) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 333 Data size: 37299 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 333 Data size: 37299 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col2 = 0L) or (_col5 is null and (_col3 >= _col2) and _col0 is not null)) (type: boolean) - Statistics: Num rows: 333 Data size: 37299 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 333 Data size: 31635 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 333 Data size: 31635 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: s1 - filterExpr: (key > '12') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '12') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: key (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: s1 - filterExpr: (key > '12') (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (key > '12') (type: boolean) - Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(key) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-4 is a root stage - Stage-5 depends on stages: Stage-4 - Stage-6 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(p_retailprice) - keys: p_mfgr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col1 (type: double) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: double) - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - TableScan - Reduce Output Operator - key expressions: _col0 (type: double) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col1 (type: double) - 1 _col0 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 6 Data size: 668 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 6 Data size: 668 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col3 (type: bigint), _col4 (type: bigint) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: double) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: double) - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: double) - 1 _col0 (type: string), _col2 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4, _col6 - Statistics: Num rows: 7 Data size: 798 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col3 is null or (_col3 = 0L) or (_col6 is not null or _col0 is null or (_col4 < _col3)) is not true) (type: boolean) - Statistics: Num rows: 7 Data size: 798 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 742 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 742 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: part - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(p_retailprice), max(p_retailprice) - keys: p_mfgr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double), _col2 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((_col2 - _col1) > 600.0D) and _col1 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(_col0) - keys: _col1 (type: double) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: double) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: double) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: part - filterExpr: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(p_retailprice), max(p_retailprice) - keys: p_mfgr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double), _col2 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (((_col2 - _col1) > 600.0D) and _col1 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), true (type: boolean), _col1 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -Manufacturer#1 1173.15 -Manufacturer#2 1690.68 -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product -PREHOOK: query: explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-4 is a root stage - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: min(p_retailprice) - keys: p_mfgr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 6 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 6 Data size: 644 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: double), _col3 (type: boolean) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 6 Data size: 740 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 6 Data size: 740 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col2 = 0L) or (_col5 is null and (_col3 >= _col2) and _col0 is not null)) (type: boolean) - Statistics: Num rows: 6 Data size: 740 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 636 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 6 Data size: 636 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(p_retailprice), min(p_retailprice) - keys: p_mfgr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double), _col2 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 - _col2) > 600.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: max(p_retailprice), min(p_retailprice) - keys: p_mfgr (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: double), _col2 (type: double) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 - _col2) > 600.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(_col0) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product -PREHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -Manufacturer#2 1690.68 -Manufacturer#1 1173.15 -PREHOOK: query: CREATE TABLE t1_n145 (c1 INT, c2 CHAR(100)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t1_n145 -POSTHOOK: query: CREATE TABLE t1_n145 (c1 INT, c2 CHAR(100)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t1_n145 -PREHOOK: query: INSERT INTO t1_n145 VALUES (null,null), (1,''), (2,'abcde'), (100,'abcdefghij') -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t1_n145 -POSTHOOK: query: INSERT INTO t1_n145 VALUES (null,null), (1,''), (2,'abcde'), (100,'abcdefghij') -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t1_n145 -POSTHOOK: Lineage: t1_n145.c1 SCRIPT [] -POSTHOOK: Lineage: t1_n145.c2 SCRIPT [] -PREHOOK: query: CREATE TABLE t2_n85 (c1 INT) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@t2_n85 -POSTHOOK: query: CREATE TABLE t2_n85 (c1 INT) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@t2_n85 -PREHOOK: query: INSERT INTO t2_n85 VALUES (null), (2), (100) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@t2_n85 -POSTHOOK: query: INSERT INTO t2_n85 VALUES (null), (2), (100) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@t2_n85 -POSTHOOK: Lineage: t2_n85.c1 SCRIPT [] -Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product -PREHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n145 -PREHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -POSTHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n145 -POSTHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2, Stage-5 - Stage-4 is a root stage - Stage-5 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n145 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: int) - outputColumnNames: c1 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col2 (type: boolean) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col2, _col3, _col4 - Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col2 (type: boolean) - outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 = 0L) or (_col4 is null and (_col2 >= _col1) and _col0 is not null)) (type: boolean) - Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: t2_n85 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: t2_n85 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: int) - outputColumnNames: c1 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(c1) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product -PREHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n145 -PREHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -POSTHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n145 -POSTHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -PREHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n145 -PREHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -POSTHOOK: query: explain SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n145 -POSTHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-4 is a root stage - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5, Stage-7 - Stage-7 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n145 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: c1 (type: int) - outputColumnNames: c1 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3 - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint), _col3 (type: bigint) - TableScan - Reduce Output Operator - key expressions: _col2 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col0, _col2, _col3, _col5 - Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col2 is null or (_col2 = 0L) or (_col5 is not null or _col0 is null or (_col3 < _col2)) is not true) (type: boolean) - Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: t2_n85 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(c1) - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: t2_n85 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - alias: t1_n145 - filterExpr: c1 is not null (type: boolean) - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: c1 is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: c1 (type: int) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) -PREHOOK: type: QUERY -PREHOOK: Input: default@t1_n145 -PREHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -POSTHOOK: query: SELECT c1 FROM t1_n145 group by c1 having c1 NOT IN (SELECT c1 FROM t2_n85 where t1_n145.c1=t2_n85.c1) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@t1_n145 -POSTHOOK: Input: default@t2_n85 -#### A masked pattern was here #### -1 -NULL -PREHOOK: query: DROP TABLE t1_n145 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@t1_n145 -PREHOOK: Output: default@t1_n145 -POSTHOOK: query: DROP TABLE t1_n145 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@t1_n145 -POSTHOOK: Output: default@t1_n145 -PREHOOK: query: DROP TABLE t2_n85 -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@t2_n85 -PREHOOK: Output: default@t2_n85 -POSTHOOK: query: DROP TABLE t2_n85 -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@t2_n85 -POSTHOOK: Output: default@t2_n85 diff --git ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out deleted file mode 100644 index 08d9791aa2..0000000000 --- ql/src/test/results/clientpositive/subquery_unqual_corr_expr.q.out +++ /dev/null @@ -1,269 +0,0 @@ -PREHOOK: query: explain -select * from src tablesample (10 rows) where lower(key) in (select key from src) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from src tablesample (10 rows) where lower(key) in (select key from src) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: lower(key) is not null (type: boolean) - Row Limit Per Split: 10 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: lower(key) is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: lower(key) (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: lower(key) (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: key (type: string), value (type: string) - TableScan - alias: src - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 lower(key) (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from src tablesample (10 rows) where lower(key) in (select key from src) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * from src tablesample (10 rows) where lower(key) in (select key from src) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -165 val_165 -238 val_238 -255 val_255 -27 val_27 -278 val_278 -311 val_311 -409 val_409 -484 val_484 -86 val_86 -98 val_98 -Warning: Shuffle Join JOIN[16][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: explain -select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-1 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - filterExpr: key is null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is null (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 = 0L) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: 0L (type: bigint) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Row Limit Per Split: 10 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: key (type: string), value (type: string) - TableScan - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: concat(_col0, _col1) (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: concat(_col0, _col1) (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col1 (type: string) - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 concat(_col0, _col1) (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 684 Data size: 165339 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: _col5 is null (type: boolean) - Statistics: Num rows: 184 Data size: 44584 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 184 Data size: 44584 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 184 Data size: 44584 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[16][tables = [src, sq_1_notin_nullcheck]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * from src tablesample (10 rows) where concat(key,value) not in (select key from src) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -165 val_165 -238 val_238 -255 val_255 -278 val_278 -27 val_27 -311 val_311 -409 val_409 -484 val_484 -86 val_86 -98 val_98 diff --git ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out deleted file mode 100644 index a26e3fd5b6..0000000000 --- ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ /dev/null @@ -1,596 +0,0 @@ -PREHOOK: query: create table src11_n0 (key1 string, value1 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src11_n0 -POSTHOOK: query: create table src11_n0 (key1 string, value1 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src11_n0 -PREHOOK: query: create table part2_n2( - p2_partkey INT, - p2_name STRING, - p2_mfgr STRING, - p2_brand STRING, - p2_type STRING, - p2_size INT, - p2_container STRING, - p2_retailprice DOUBLE, - p2_comment STRING -) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@part2_n2 -POSTHOOK: query: create table part2_n2( - p2_partkey INT, - p2_name STRING, - p2_mfgr STRING, - p2_brand STRING, - p2_type STRING, - p2_size INT, - p2_container STRING, - p2_retailprice DOUBLE, - p2_comment STRING -) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@part2_n2 -PREHOOK: query: explain select * from src11_n0 where src11_n0.key1 in (select key from src where src11_n0.value1 = value and key > '9') -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src11_n0 -#### A masked pattern was here #### -POSTHOOK: query: explain select * from src11_n0 where src11_n0.key1 in (select key from src where src11_n0.value1 = value and key > '9') -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src11_n0 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src11_n0 - filterExpr: ((key1 > '9') and value1 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key1 > '9') and value1 is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key1 (type: string), value1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: src - filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 91 Data size: 16251 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 91 Data size: 16251 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select * from src a where a.key in (select key from src where a.value = value and key > '9') -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain select * from src a where a.key in (select key from src where a.value = value and key > '9') -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select * -from src b -where b.key in - (select distinct key - from src - where b.value = value and key > '9' - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: explain -select * -from src b -where b.key in - (select distinct key - from src - where b.value = value and key > '9' - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src - filterExpr: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select p_mfgr, b.p_name, p_size -from part b -where b.p_name not in - (select p_name - from (select p_mfgr, p_name, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a - where r <= 2 and b.p_mfgr = p_mfgr - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: explain -select p_mfgr, b.p_name, p_size -from part b -where b.p_name not in - (select p_name - from (select p_mfgr, p_name, p_size, rank() over(partition by p_mfgr order by p_size) as r from part) a - where r <= 2 and b.p_mfgr = p_mfgr - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 - Stage-2 depends on stages: Stage-1, Stage-6 - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: part - filterExpr: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_size (type: int) - null sort order: az - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: p_name (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col1, _col2, _col5 - Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col1: string, _col2: string, _col5: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col5 ASC NULLS LAST - partition by: _col2 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col5 - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(), count(_col0) - keys: _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string), _col2 (type: int) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4, _col5 - Statistics: Num rows: 33 Data size: 7695 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 33 Data size: 7695 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: string) - Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col7 - Statistics: Num rows: 38 Data size: 8914 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col4 is null or (_col4 = 0L) or (_col7 is not null or _col0 is null or (_col5 < _col4)) is not true) (type: boolean) - Statistics: Num rows: 38 Data size: 8914 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 38 Data size: 8474 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 38 Data size: 8474 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: part - filterExpr: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: p_mfgr is not null (type: boolean) - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: p_mfgr (type: string), p_size (type: int) - null sort order: az - sort order: ++ - Map-reduce partition columns: p_mfgr (type: string) - Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: p_name (type: string) - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) - outputColumnNames: _col1, _col2, _col5 - Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col1: string, _col2: string, _col5: int - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col5 ASC NULLS LAST - partition by: _col2 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col5 - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((rank_window_0 <= 2) and _col1 is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), true (type: boolean), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - diff --git ql/src/test/results/clientpositive/tablevalues.q.out ql/src/test/results/clientpositive/tablevalues.q.out deleted file mode 100644 index 149cde52c6..0000000000 --- ql/src/test/results/clientpositive/tablevalues.q.out +++ /dev/null @@ -1,1020 +0,0 @@ -PREHOOK: query: CREATE TABLE mytbl_n1 AS -SELECT key, value -FROM src -ORDER BY key -LIMIT 5 -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@mytbl_n1 -POSTHOOK: query: CREATE TABLE mytbl_n1 AS -SELECT key, value -FROM src -ORDER BY key -LIMIT 5 -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@mytbl_n1 -POSTHOOK: Lineage: mytbl_n1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: mytbl_n1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: EXPLAIN -INSERT INTO mytbl_n1(key,value) -SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) -WHERE b = 9 -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@mytbl_n1 -POSTHOOK: query: EXPLAIN -INSERT INTO mytbl_n1(key,value) -SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) -WHERE b = 9 -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@mytbl_n1 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 - Stage-5 - Stage-6 depends on stages: Stage-5 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: _dummy_table - Row Limit Per Split: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(const struct(1,2),const struct(3,4)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 1 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Filter Operator - predicate: (col2 = 9) (type: boolean) - Statistics: Num rows: 1 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: CAST( col1 AS STRING) (type: string), '9' (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mytbl_n1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: key, value - Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct), _col1 (type: struct) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-7 - Conditional Operator - - Stage: Stage-4 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-0 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mytbl_n1 - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.mytbl_n1 - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mytbl_n1 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.mytbl_n1 - - Stage: Stage-6 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: INSERT INTO mytbl_n1(key,value) -SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) -WHERE b = 9 -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Output: default@mytbl_n1 -POSTHOOK: query: INSERT INTO mytbl_n1(key,value) -SELECT a,b as c FROM TABLE(VALUES(1,2),(3,4)) AS vc(a,b) -WHERE b = 9 -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Output: default@mytbl_n1 -POSTHOOK: Lineage: mytbl_n1.key SCRIPT [] -POSTHOOK: Lineage: mytbl_n1.value EXPRESSION [] -PREHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t - LATERAL VIEW - INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t - LATERAL VIEW - INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - expressions: col3 (type: string), col4 (type: int), col5 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t - LATERAL VIEW - INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t - LATERAL VIEW - INLINE(array(struct('A', 10, t.key),struct('B', 20, t.key))) tf AS col1, col2, col3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -A 10 0 -B 20 0 -A 10 0 -B 20 0 -A 10 0 -B 20 0 -A 10 10 -B 20 10 -A 10 100 -B 20 100 -PREHOOK: query: EXPLAIN -SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: _dummy_table - Row Limit Per Split: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - expressions: col1 (type: string), col2 (type: int), col3 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -POSTHOOK: query: SELECT INLINE(array(struct('A', 10, 30),struct('B', 20, 30))) AS (col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -A 10 30 -B 20 30 -PREHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30.0),('B', 20, 30.0)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30.0),('B', 20, 30.0)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: _dummy_table - Row Limit Per Split: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3640 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 1 Data size: 3640 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - expressions: col1 (type: string), col2 (type: int), col3 (type: decimal(2,0)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -A 10 30 -B 20 30 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - (SELECT key, value FROM mytbl_n1) t -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - (SELECT key, value FROM mytbl_n1) t -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: _dummy_table - Row Limit Per Split: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: col1 (type: string), col2 (type: int), col3 (type: int) - TableScan - alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - (SELECT key, value FROM mytbl_n1) t -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - (SELECT key, value FROM mytbl_n1) t -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -B 20 30 -B 20 30 -B 20 30 -B 20 30 -B 20 30 -A 10 30 -A 10 30 -A 10 30 -A 10 30 -A 10 30 -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: _dummy_table - Row Limit Per Split: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: col1 (type: string), col2 (type: int), col3 (type: int) - TableScan - alias: _dummy_table - Row Limit Per Split: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(const struct('A',10),const struct('B',20)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2440 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 1 Data size: 2440 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3), - TABLE(VALUES('A', 10),('B', 20)) AS tf2(col1, col2) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -#### A masked pattern was here #### -B 20 30 -B 20 30 -A 10 30 -A 10 30 -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: _dummy_table - Row Limit Per Split: 1 - Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(const struct('A',10,30),const struct('B',20,30)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 2560 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: col1 (type: string), col2 (type: int), col3 (type: int) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string), _col2 (type: int), _col3 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product -PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: _dummy_database@_dummy_table -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - TABLE(VALUES('A', 10, 30),('B', 20, 30)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: _dummy_database@_dummy_table -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -B 20 30 -A 10 30 -B 20 30 -A 10 30 -B 20 30 -A 10 30 -B 20 30 -A 10 30 -B 20 30 -A 10 30 -PREHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - expressions: col3 (type: string), col4 (type: int), col5 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col1, tf.col2, tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -A 10 0 -B 20 0 -A 10 0 -B 20 0 -A 10 0 -B 20 0 -A 10 10 -B 20 10 -A 10 100 -B 20 100 -PREHOOK: query: EXPLAIN -SELECT t.key -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT t.key -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - expressions: col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT t.key -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT t.key -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -0 -0 -0 -0 -0 -0 -10 -10 -100 -100 -PREHOOK: query: EXPLAIN -SELECT tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(struct(key,value,'A',10,key),struct(key,value,'B',20,key)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 5 Data size: 41000 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - expressions: col5 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col3 -FROM - (SELECT key, value FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.key),('B', 20, t.key)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -0 -0 -0 -0 -0 -0 -10 -10 -100 -100 -PREHOOK: query: EXPLAIN -SELECT tf.col3 -FROM - (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -SELECT tf.col3 -FROM - (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: mytbl_n1 - Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: 0 (type: int), key (type: string) - null sort order: az - sort order: +- - Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 1770 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col0 DESC NULLS LAST - partition by: 0 - raw input shape: - window functions: - window function definition - alias: row_number_window_0 - name: row_number - window function: GenericUDAFRowNumberEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 5 Data size: 1770 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: array(struct(row_number_window_0,'A',10,row_number_window_0),struct(row_number_window_0,'B',20,row_number_window_0)) (type: array>) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 13400 Basic stats: COMPLETE Column stats: COMPLETE - UDTF Operator - Statistics: Num rows: 5 Data size: 13400 Basic stats: COMPLETE Column stats: COMPLETE - function name: inline - Select Operator - expressions: col4 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT tf.col3 -FROM - (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) -PREHOOK: type: QUERY -PREHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT tf.col3 -FROM - (SELECT row_number() over (order by key desc) as r FROM mytbl_n1) t, - LATERAL TABLE(VALUES('A', 10, t.r),('B', 20, t.r)) AS tf(col1, col2, col3) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@mytbl_n1 -#### A masked pattern was here #### -1 -1 -2 -2 -3 -3 -4 -4 -5 -5 diff --git ql/src/test/results/clientpositive/temp_table_insert2_overwrite_partitions.q.out ql/src/test/results/clientpositive/temp_table_insert2_overwrite_partitions.q.out deleted file mode 100644 index a5314e944c..0000000000 --- ql/src/test/results/clientpositive/temp_table_insert2_overwrite_partitions.q.out +++ /dev/null @@ -1,379 +0,0 @@ -PREHOOK: query: CREATE DATABASE db1 -PREHOOK: type: CREATEDATABASE -PREHOOK: Output: database:db1 -POSTHOOK: query: CREATE DATABASE db1 -POSTHOOK: type: CREATEDATABASE -POSTHOOK: Output: database:db1 -PREHOOK: query: CREATE DATABASE db2 -PREHOOK: type: CREATEDATABASE -PREHOOK: Output: database:db2 -POSTHOOK: query: CREATE DATABASE db2 -POSTHOOK: type: CREATEDATABASE -POSTHOOK: Output: database:db2 -PREHOOK: query: CREATE TEMPORARY TABLE db1.sourceTable_temp (one string,two string) PARTITIONED BY (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:db1 -PREHOOK: Output: db1@sourceTable_temp -POSTHOOK: query: CREATE TEMPORARY TABLE db1.sourceTable_temp (one string,two string) PARTITIONED BY (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:db1 -POSTHOOK: Output: db1@sourceTable_temp -PREHOOK: query: load data local inpath '../../data/files/kv1.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: db1@sourcetable_temp -POSTHOOK: query: load data local inpath '../../data/files/kv1.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: db1@sourcetable_temp -POSTHOOK: Output: db1@sourcetable_temp@ds=2011-11-11 -PREHOOK: query: load data local inpath '../../data/files/kv3.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: db1@sourcetable_temp@ds=2011-11-11 -POSTHOOK: query: load data local inpath '../../data/files/kv3.txt' INTO TABLE db1.sourceTable_temp partition(ds='2011-11-11') -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: db1@sourcetable_temp@ds=2011-11-11 -PREHOOK: query: CREATE TEMPORARY TABLE db2.destinTable_temp (one string,two string) PARTITIONED BY (ds string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:db2 -PREHOOK: Output: db2@destinTable_temp -POSTHOOK: query: CREATE TEMPORARY TABLE db2.destinTable_temp (one string,two string) PARTITIONED BY (ds string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:db2 -POSTHOOK: Output: db2@destinTable_temp -PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -PREHOOK: type: QUERY -PREHOOK: Input: db1@sourcetable_temp -PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 -POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: db1@sourcetable_temp -POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: sourcetable_temp - filterExpr: (ds = '2011-11-11') (type: boolean) - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: -- - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: db2.destintable_temp - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string) - outputColumnNames: one, two, ds - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') - keys: ds (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - partition: - ds 2011-11-11 - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: db2.destintable_temp - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: one, two - Column Types: string, string - Table: db2.destintable_temp - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -PREHOOK: type: QUERY -PREHOOK: Input: db1@sourcetable_temp -PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 -POSTHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: db1@sourcetable_temp -POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 -POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).one SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:one, type:string, comment:null), ] -POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).two SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:two, type:string, comment:null), ] -PREHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc -PREHOOK: type: QUERY -PREHOOK: Input: db2@destintable_temp -PREHOOK: Input: db2@destintable_temp@ds=2011-11-11 -#### A masked pattern was here #### -POSTHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc -POSTHOOK: type: QUERY -POSTHOOK: Input: db2@destintable_temp -POSTHOOK: Input: db2@destintable_temp@ds=2011-11-11 -#### A masked pattern was here #### -98 val_98 -98 val_98 -98 val_98 -97 val_97 -97 val_97 -PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -PREHOOK: type: QUERY -PREHOOK: Input: db1@sourcetable_temp -PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 -POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: db1@sourcetable_temp -POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0, Stage-3 - Stage-3 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: sourcetable_temp - filterExpr: (ds = '2011-11-11') (type: boolean) - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: one (type: string), two (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: zz - sort order: -- - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - TopN Hash Memory Usage: 0.1 - Execution mode: vectorized - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 124 Data size: 40480 Basic stats: PARTIAL Column stats: NONE - Limit - Number of rows: 5 - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: db2.destintable_temp - Select Operator - expressions: _col0 (type: string), _col1 (type: string), '2011-11-11' (type: string) - outputColumnNames: one, two, ds - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: compute_stats(one, 'hll'), compute_stats(two, 'hll') - keys: ds (type: string) - minReductionHashAggr: 0.99 - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Move Operator - tables: - partition: - ds 2011-11-11 - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: db2.destintable_temp - - Stage: Stage-2 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: one, two - Column Types: string, string - Table: db2.destintable_temp - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 1630 Basic stats: PARTIAL Column stats: NONE - value expressions: _col1 (type: struct), _col2 (type: struct) - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 652 Basic stats: PARTIAL Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -PREHOOK: type: QUERY -PREHOOK: Input: db1@sourcetable_temp -PREHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -PREHOOK: Output: db2@destintable_temp@ds=2011-11-11 -POSTHOOK: query: INSERT OVERWRITE TABLE db2.destinTable_temp PARTITION (ds='2011-11-11') - SELECT one,two FROM db1.sourceTable_temp WHERE ds='2011-11-11' order by one desc, two desc limit 5 -POSTHOOK: type: QUERY -POSTHOOK: Input: db1@sourcetable_temp -POSTHOOK: Input: db1@sourcetable_temp@ds=2011-11-11 -POSTHOOK: Output: db2@destintable_temp@ds=2011-11-11 -POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).one SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:one, type:string, comment:null), ] -POSTHOOK: Lineage: destintable_temp PARTITION(ds=2011-11-11).two SIMPLE [(sourcetable_temp)sourcetable_temp.FieldSchema(name:two, type:string, comment:null), ] -PREHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc -PREHOOK: type: QUERY -PREHOOK: Input: db2@destintable_temp -PREHOOK: Input: db2@destintable_temp@ds=2011-11-11 -#### A masked pattern was here #### -POSTHOOK: query: select one,two from db2.destinTable_temp order by one desc, two desc -POSTHOOK: type: QUERY -POSTHOOK: Input: db2@destintable_temp -POSTHOOK: Input: db2@destintable_temp@ds=2011-11-11 -#### A masked pattern was here #### -98 val_98 -98 val_98 -98 val_98 -97 val_97 -97 val_97 -PREHOOK: query: drop table db2.destinTable_temp -PREHOOK: type: DROPTABLE -PREHOOK: Input: db2@destintable_temp -PREHOOK: Output: db2@destintable_temp -POSTHOOK: query: drop table db2.destinTable_temp -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: db2@destintable_temp -POSTHOOK: Output: db2@destintable_temp -PREHOOK: query: drop table db1.sourceTable_temp -PREHOOK: type: DROPTABLE -PREHOOK: Input: db1@sourcetable_temp -PREHOOK: Output: db1@sourcetable_temp -POSTHOOK: query: drop table db1.sourceTable_temp -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: db1@sourcetable_temp -POSTHOOK: Output: db1@sourcetable_temp -PREHOOK: query: DROP DATABASE db1 -PREHOOK: type: DROPDATABASE -PREHOOK: Input: database:db1 -PREHOOK: Output: database:db1 -POSTHOOK: query: DROP DATABASE db1 -POSTHOOK: type: DROPDATABASE -POSTHOOK: Input: database:db1 -POSTHOOK: Output: database:db1 -PREHOOK: query: DROP DATABASE db2 -PREHOOK: type: DROPDATABASE -PREHOOK: Input: database:db2 -PREHOOK: Output: database:db2 -POSTHOOK: query: DROP DATABASE db2 -POSTHOOK: type: DROPDATABASE -POSTHOOK: Input: database:db2 -POSTHOOK: Output: database:db2 diff --git ql/src/test/results/clientpositive/temp_table_join1.q.out ql/src/test/results/clientpositive/temp_table_join1.q.out deleted file mode 100644 index 2312784c00..0000000000 --- ql/src/test/results/clientpositive/temp_table_join1.q.out +++ /dev/null @@ -1,348 +0,0 @@ -PREHOOK: query: CREATE TABLE src_nontemp AS SELECT * FROM src limit 10 -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@src_nontemp -POSTHOOK: query: CREATE TABLE src_nontemp AS SELECT * FROM src limit 10 -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_nontemp -POSTHOOK: Lineage: src_nontemp.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_nontemp.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: CREATE TEMPORARY TABLE src_temp AS SELECT * FROM src limit 10 -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@src_temp -POSTHOOK: query: CREATE TEMPORARY TABLE src_temp AS SELECT * FROM src limit 10 -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_temp -PREHOOK: query: EXPLAIN -FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src_nontemp -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_nontemp -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src_nontemp -#### A masked pattern was here #### -POSTHOOK: query: FROM src_nontemp src1 JOIN src_nontemp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_nontemp -#### A masked pattern was here #### -165 val_165 -238 val_238 -255 val_255 -27 val_27 -278 val_278 -311 val_311 -409 val_409 -484 val_484 -86 val_86 -98 val_98 -PREHOOK: query: EXPLAIN -FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src_nontemp -PREHOOK: Input: default@src_temp -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_nontemp -POSTHOOK: Input: default@src_temp -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE - TableScan - alias: src2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 11 Data size: 957 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src_nontemp -PREHOOK: Input: default@src_temp -#### A masked pattern was here #### -POSTHOOK: query: FROM src_nontemp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_nontemp -POSTHOOK: Input: default@src_temp -#### A masked pattern was here #### -165 val_165 -238 val_238 -255 val_255 -27 val_27 -278 val_278 -311 val_311 -409 val_409 -484 val_484 -86 val_86 -98 val_98 -PREHOOK: query: EXPLAIN -FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src_temp -#### A masked pattern was here #### -POSTHOOK: query: EXPLAIN -FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_temp -#### A masked pattern was here #### -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src1 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: src2 - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: z - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2 - Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src_temp -#### A masked pattern was here #### -POSTHOOK: query: FROM src_temp src1 JOIN src_temp src2 ON (src1.key = src2.key) -SELECT src1.key, src2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_temp -#### A masked pattern was here #### -165 val_165 -238 val_238 -255 val_255 -27 val_27 -278 val_278 -311 val_311 -409 val_409 -484 val_484 -86 val_86 -98 val_98 -PREHOOK: query: DROP TABLE src_nontemp -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@src_nontemp -PREHOOK: Output: default@src_nontemp -POSTHOOK: query: DROP TABLE src_nontemp -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@src_nontemp -POSTHOOK: Output: default@src_nontemp -PREHOOK: query: DROP TABLE src_temp -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@src_temp -PREHOOK: Output: default@src_temp -POSTHOOK: query: DROP TABLE src_temp -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@src_temp -POSTHOOK: Output: default@src_temp